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

    Neuronpedia

    INDEX
    Explanations

    Scale

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JM
    -0.08
     Runner
    -0.07
    _FIN
    -0.07
     Blonde
    -0.07
     juven
    -0.07
     DOWNLOAD
    -0.07
     Ella
    -0.07
     Ronald
    -0.07
     Compile
    -0.07
    ENA
    -0.07
    POSITIVE LOGITS
    .getString
    0.07
    قط
    0.07
    ativo
    0.07
    保護政策
    0.07
    noxious
    0.07
    方式
    0.07
    Another
    0.06
    ستراتيجي
    0.06
    FormatException
    0.06
     minimise
    0.06
    Act Density 0.002%

    No Known Activations