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

    Neuronpedia

    INDEX
    Explanations

    London

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    滚球
    -0.07
    extended
    -0.07
     fined
    -0.07
    IFF
    -0.07
    ॲ
    -0.07
     inaugur
    -0.07
    👡
    -0.07
    TintColor
    -0.06
    IllegalAccessException
    -0.06
    床上
    -0.06
    POSITIVE LOGITS
    ?s
    0.07
    更强
    0.07
    itas
    0.07
     counting
    0.07
    "]["
    0.07
     [--
    0.06
    _NS
    0.06
    ваться
    0.06
     sẵn
    0.06
     overlap
    0.06
    Act Density 0.010%

    No Known Activations