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

    Neuronpedia

    INDEX
    Explanations

    -width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    海尔
    -0.07
    气候
    -0.06
    _hist
    -0.06
     subsidized
    -0.06
     unser
    -0.06
    获批
    -0.06
    喜剧
    -0.06
    /react
    -0.06
    ﷻ
    -0.06
    北海
    -0.06
    POSITIVE LOGITS
     usuarios
    0.07
    码
    0.07
    ção
    0.07
    -lined
    0.07
    ят
    0.06
     shares
    0.06
    IBC
    0.06
    .Inter
    0.06
    غل
    0.06
     كما
    0.06
    Act Density 0.001%

    No Known Activations