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

    Neuronpedia

    INDEX
    Explanations

    women and men / gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effort
    -0.07
    Texto
    -0.07
    _Key
    -0.07
    ocolate
    -0.07
    用餐
    -0.06
    艰
    -0.06
    (express
    -0.06
    MediaPlayer
    -0.06
     такого
    -0.06
    损伤
    -0.06
    POSITIVE LOGITS
     Ling
    0.07
    㛹
    0.07
     financing
    0.07
    玕
    0.06
     אחת
    0.06
    ᵨ
    0.06
    .forward
    0.06
    ,column
    0.06
     Público
    0.06
    锒
    0.06
    Act Density 0.034%

    No Known Activations