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

    Neuronpedia

    INDEX
    Explanations

    software license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buat
    -0.07
    .Some
    -0.07
    Duration
    -0.07
    咔
    -0.07
    日本人
    -0.06
    הז
    -0.06
    五大
    -0.06
    个小
    -0.06
     данной
    -0.06
    之时
    -0.06
    POSITIVE LOGITS
     bomb
    0.07
    .getExternal
    0.07
     searching
    0.07
    bab
    0.07
    检验
    0.07
    螱
    0.07
    POS
    0.07
    startIndex
    0.07
    международ
    0.07
    itial
    0.07
    Act Density 0.000%

    No Known Activations