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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Drive
    -0.07
    owell
    -0.07
     recovering
    -0.06
     Brushes
    -0.06
     �
    -0.06
     strives
    -0.06
    Quarter
    -0.06
     Step
    -0.06
     realize
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    licas
    0.06
     rotterdam
    0.06
     недостат
    0.06
    .GetDirectoryName
    0.06
     yytype
    0.06
    _UNDEF
    0.06
    ufac
    0.06
     spectrum
    0.06
    ingleton
    0.06
    pectrum
    0.06
    Act Density 0.023%

    No Known Activations