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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    accumulator
    -0.08
    _AREA
    -0.07
     Gad
    -0.07
    是一项
    -0.07
    氛
    -0.07
    adaptive
    -0.07
    ��
    -0.07
     SPORT
    -0.07
    _bitmap
    -0.07
     bỏ
    -0.07
    POSITIVE LOGITS
     Elizabeth
    0.08
    周五
    0.07
    お客様
    0.07
     MLB
    0.07
    olkien
    0.06
    reachable
    0.06
    Daniel
    0.06
    工厂
    0.06
    厂区
    0.06
    و
    0.06
    Act Density 0.001%

    No Known Activations