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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ideal
    -0.07
    етом
    -0.07
    _launch
    -0.06
     ions
    -0.06
     роботи
    -0.06
     Emit
    -0.06
    660
    -0.06
    *$
    -0.06
     expression
    -0.06
     indu
    -0.06
    POSITIVE LOGITS
    _password
    0.09
     IMPORTANT
    0.07
    ograf
    0.07
    Password
    0.07
    compass
    0.06
    .multipart
    0.06
    _generation
    0.06
     بوابة
    0.06
    .bounds
    0.06
     london
    0.06
    Act Density 0.006%

    No Known Activations