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

    Neuronpedia

    INDEX
    Explanations

    reasons and causes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gill
    -0.07
     Shank
    -0.07
    �
    -0.06
    引领
    -0.06
    TMP
    -0.06
     Zheng
    -0.06
    各单位
    -0.06
     sanction
    -0.06
    jourd
    -0.06
    AntiForgeryToken
    -0.06
    POSITIVE LOGITS
    ぱ
    0.08
     Ada
    0.07
    搭配
    0.07
     Otto
    0.07
     типа
    0.07
    ENTA
    0.07
     salvage
    0.07
    ″
    0.07
    再说
    0.07
    ugador
    0.06
    Act Density 0.104%

    No Known Activations