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

    Neuronpedia

    INDEX
    Explanations

    statements involving agreement or disagreement percentages related to opinions on gender roles and societal expectations

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

    Percentages

    np_acts-logits-general · gemini-2.0-flash

    percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WindowConstants
    -0.66
     ویکی‌پدی
    -0.65
    expandindo
    -0.64
     Italijanski
    -0.60
    StructEnd
    -0.60
    دانشنامهٔ
    -0.57
    GraphicsUnit
    -0.56
    -0.56
     disambiguazione
    -0.55
     AssemblyCulture
    -0.54
    POSITIVE LOGITS
     parap
    0.50
    onView
    0.49
     NgModule
    0.48
     Fuego
    0.48
    __':
    0.48
    structors
    0.47
    odotus
    0.47
     Hie
    0.47
    $$
    0.47
     Silt
    0.46
    Act Density 0.318%

    No Known Activations