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

    Neuronpedia

    INDEX
    Explanations

    election disputes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    終於
    -0.08
    丙
    -0.07
     phiên
    -0.07
     equals
    -0.07
    against
    -0.07
     suit
    -0.07
     Pip
    -0.07
     с
    -0.07
     circus
    -0.07
     could
    -0.07
    POSITIVE LOGITS
    垴
    0.07
    ┥
    0.07
    ומי
    0.07
    혭
    0.07
    搜索
    0.07
    商用车
    0.07
    -known
    0.07
    受贿
    0.07
    是一项
    0.07
    媖
    0.07
    Act Density 0.030%

    No Known Activations