Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to discrimination based on various demographic factors such as race, gender, and religion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Discrimination based on protected classes

    np_acts-logits-general · gemini-2.0-flash

    gender, race, sex, pregnancy discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.79
     برانيه
    -0.69
    RenderAtEndOf
    -0.69
    contentLoaded
    -0.65
    ngdoc
    -0.63
    migrationBuilder
    -0.62
     kasarigan
    -0.61
    Pranala
    -0.60
    UnitTesting
    -0.60
    PageFactory
    -0.59
    POSITIVE LOGITS
     gender
    1.53
     race
    1.48
     ethnicity
    1.40
     nationality
    1.33
     religion
    1.23
    gender
    1.18
     Race
    1.18
     sex
    1.15
     Gender
    1.12
    race
    1.11
    Act Density 0.568%

    No Known Activations