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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يجب
    -0.07
     decis
    -0.07
    .change
    -0.07
    .rar
    -0.06
    isChecked
    -0.06
     converters
    -0.06
    νομ
    -0.06
    define
    -0.06
     创建
    -0.06
     разом
    -0.06
    POSITIVE LOGITS
     +
    0.08
    TY
    0.07
    سم
    0.06
    ोक
    0.06
    -date
    0.06
     Lonely
    0.06
    +
    0.06
    Introduced
    0.06
    其中
    0.06
    ки
    0.06
    Act Density 0.013%

    No Known Activations