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

    Neuronpedia

    INDEX
    Explanations

    Arbitrary bodies of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ={{
    -0.07
     Bankası
    -0.06
    ）
    -0.06
    UED
    -0.06
    면
    -0.06
     한국
    -0.06
     Entries
    -0.06
    .eval
    -0.06
     patron
    -0.06
    inth
    -0.06
    POSITIVE LOGITS
    (HttpServletRequest
    0.07
    =min
    0.06
    asion
    0.06
    素
    0.06
     immoral
    0.06
     Abstract
    0.06
    MainWindow
    0.06
     广
    0.06
    uzz
    0.06
     musí
    0.06
    Act Density 0.000%

    No Known Activations