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

    Neuronpedia

    INDEX
    Explanations

    gender roles, acting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .minute
    -0.07
     successful
    -0.06
    니스
    -0.06
    (pub
    -0.06
    _ENUM
    -0.06
     privileged
    -0.06
    $status
    -0.06
     quotations
    -0.06
     アル
    -0.06
    .flat
    -0.06
    POSITIVE LOGITS
    rech
    0.07
    Při
    0.07
    續
    0.06
     tread
    0.06
    一级
    0.06
    -hover
    0.06
    ísk
    0.06
    Gatt
    0.06
    ł
    0.06
    خصوص
    0.06
    Act Density 0.019%

    No Known Activations