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

    Neuronpedia

    INDEX
    Explanations

    code and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (isinstance
    -0.06
    سط
    -0.06
    DOT
    -0.06
     Си
    -0.06
    коп
    -0.06
    aval
    -0.06
    ymology
    -0.06
    編
    -0.06
    ILT
    -0.06
     apopt
    -0.06
    POSITIVE LOGITS
     modern
    0.07
    _expected
    0.07
     convictions
    0.07
    يق
    0.07
     SRC
    0.07
    .getContext
    0.06
    信息
    0.06
     suppose
    0.06
    çok
    0.06
     psycho
    0.06
    Act Density 0.000%

    No Known Activations