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

    Neuronpedia

    INDEX
    Explanations

    UE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coy
    -0.07
    _arc
    -0.06
    計算
    -0.06
     довольно
    -0.06
     рамках
    -0.06
    这是
    -0.06
    _pw
    -0.06
     Tobacco
    -0.06
     Leather
    -0.06
     mutlu
    -0.06
    POSITIVE LOGITS
    storeId
    0.07
    PasswordField
    0.06
     unfavorable
    0.06
     */,↵
    0.06
    _CUDA
    0.06
    xBD
    0.06
    umno
    0.06
     Stainless
    0.06
     skon
    0.06
     womens
    0.06
    Act Density 0.008%

    No Known Activations