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

    Neuronpedia

    INDEX
    Explanations

    object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    껴
    -0.07
     Trim
    -0.07
    ERV
    -0.07
    栈
    -0.06
    😋
    -0.06
    镞
    -0.06
     flurry
    -0.06
    良心
    -0.06
    تابع
    -0.06
    ượ
    -0.06
    POSITIVE LOGITS
    -information
    0.07
    wan
    0.07
    pping
    0.07
    озвращает
    0.07
    дон
    0.07
     Cabinets
    0.07
    .getDouble
    0.06
     отношения
    0.06
    们的
    0.06
     pager
    0.06
    Act Density 0.000%

    No Known Activations