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

    Neuronpedia

    INDEX
    Explanations

    references to gender, particularly focusing on girls and their experiences or roles in various contexts

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

    boys and girls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.67
    basicConfig
    -0.66
    AnchorStyles
    -0.66
    MemoryWarning
    -0.64
    sizeCache
    -0.63
    Rptr
    -0.63
    ChildScrollView
    -0.62
    BufferException
    -0.61
    ロウィン
    -0.60
    UrlResolution
    -0.59
    POSITIVE LOGITS
     girls
    0.83
     Girls
    0.81
    Girls
    0.79
     boys
    0.72
     GIRLS
    0.67
    girls
    0.63
     Boys
    0.62
    Boys
    0.59
     BOYS
    0.56
    boys
    0.55
    Act Density 0.011%

    No Known Activations