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

    Neuronpedia

    INDEX
    Explanations

    integrity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.73
     Majefty
    -0.69
     Efq
    -0.69
     Verſ
    -0.66
     Monfieur
    -0.66
     Hift
    -0.65
     Whig
    -0.63
    ukses
    -0.63
     auffi
    -0.63
     Chaldean
    -0.63
    POSITIVE LOGITS
    DoubleQuotes
    0.65
    WithIOException
    0.60
     estekak
    0.56
    LayoutStyle
    0.52
     andar
    0.49
    SourceChecksum
    0.48
     Carr
    0.45
     and
    0.45
     parseFrom
    0.45
     Fan
    0.44
    Act Density 0.016%

    No Known Activations