# Gender Neuron Masking on GCGender Feminine Source: [Gender Neuron Masking on GCGender Feminine]() Collection index: [llms.txt]() Data updated: 2026-06-01T08:04:25.749Z Evaluation of model performance on the Gender Neuron Masking task using the GCGender Feminine dataset, focusing on term counts, mention ratios, and delta ratios across male (M), female (F), and neutral (N) categories. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Gender Neuron Masking | | Dataset (including any stated split) | GCGender Feminine | | Metric | Term Count (M) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 4 of 4 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Term Count (M)](): Higher is better; unit: SCALAR. - [Term Count (F)](): Higher is better; unit: SCALAR. - [Term Count (N)](): Higher is better; unit: SCALAR. - [Mention Ratio (M)](): Higher is better; unit: PERCENT. - [Mention Ratio (F)](): Higher is better; unit: PERCENT. - [Mention Ratio (N)](): Higher is better; unit: PERCENT. - [Delta Ratio (M)](): Higher is better; unit: PERCENT. - [Delta Ratio (F)](): Higher is better; unit: PERCENT. - [Delta Ratio (N)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Term Count (M) | Result date | Report paper | | --- | --- | --- | --- | | sNeuron-TST | 0.71 | Not recorded | 6a1d1213dbd7150506f83fef | | LAPE | 0.24 | Not recorded | 6a1d1213dbd7150506f83fef | | Baseline | 0.23 | Not recorded | 6a1d1213dbd7150506f83fef | | Ours | 0.22 | Not recorded | 6a1d1213dbd7150506f83fef | ### sNeuron-TST Term Count (M): 0.71. Result ID: 6a1d3c4cfbc373592c163a2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama 3.1"}. This record does not assert independent reproduction. ### LAPE Term Count (M): 0.24. Result ID: 6a1d3c4cfbc373592c163a2c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama 3.1"}. This record does not assert independent reproduction. ### Baseline Term Count (M): 0.23. Result ID: 6a1d3c4cfbc373592c163a2a. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Llama 3.1"}. This record does not assert independent reproduction. ### Ours Term Count (M): 0.22. Result ID: 6a1d3c4cfbc373592c163a2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama 3.1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.