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

    Neuronpedia

    INDEX
    Explanations

    multi-factor authentication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liğ
    -0.07
    очку
    -0.07
    잖
    -0.06
    Index
    -0.06
    ルド
    -0.06
    飯
    -0.06
    clock
    -0.06
     приготовления
    -0.06
     Successful
    -0.06
    يم
    -0.06
    POSITIVE LOGITS
    LL
    0.07
    γων
    0.07
    ेवल
    0.07
    _env
    0.06
     placing
    0.06
     fairly
    0.06
    ll
    0.06
     Hava
    0.06
     FirebaseDatabase
    0.06
     vomiting
    0.06
    Act Density 0.009%

    No Known Activations