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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ổ
    -0.07
    inc
    -0.07
    检
    -0.07
     Coh
    -0.06
     minutos
    -0.06
    尕
    -0.06
     Tran
    -0.06
    殄
    -0.06
    operation
    -0.06
    Ill
    -0.06
    POSITIVE LOGITS
     sperma
    0.09
    .fromString
    0.07
     >>=
    0.07
    거래
    0.07
     جدا
    0.07
    *',
    0.07
     הישראלי
    0.07
    让用户
    0.07
    .getX
    0.07
     منهم
    0.07
    Act Density 0.009%

    No Known Activations