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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bad
    -0.07
     Encoder
    -0.07
    .did
    -0.06
     hashtags
    -0.06
    Destroy
    -0.06
    ifter
    -0.06
     PyTuple
    -0.06
    anya
    -0.06
     Managed
    -0.06
     ‎
    -0.06
    POSITIVE LOGITS
     Shia
    0.07
    чна
    0.06
    .FileInputStream
    0.06
    (rx
    0.06
    sik
    0.06
     транспор
    0.06
     BrowserModule
    0.06
    iền
    0.06
    _UFunction
    0.06
     Герм
    0.06
    Act Density 0.037%

    No Known Activations