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

    Neuronpedia

    INDEX
    Explanations

    references to female characters and their relationships or attributes

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

    Refers to a woman or her actions

    np_acts-logits-general · gemini-2.0-flash

    female pronouns and related actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.43
    僕が
    -0.43
     僕
    -0.40
    UnsafeEnabled
    -0.40
     buddies
    -0.39
    sividad
    -0.39
    })->
    -0.39
    choly
    -0.38
     Jonny
    -0.38
    zwa
    -0.38
    POSITIVE LOGITS
    Obrigada
    0.68
     herself
    0.67
     lesbian
    0.65
     hendes
    0.63
    حياتها
    0.60
     Women
    0.57
     करती
    0.57
     businesswoman
    0.56
    🏻‍♀️
    0.56
    FormTagHelper
    0.55
    Act Density 0.621%

    No Known Activations