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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical fractions and their parsing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Methods related to number operations testing

    np_acts-logits-general · gemini-2.0-flash

    testing decimal floating point operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    createConnection
    -0.46
    ilarities
    -0.46
    Bronnen
    -0.45
    erville
    -0.45
     hinges
    -0.42
    orption
    -0.39
     petting
    -0.39
     Verbindung
    -0.39
    unlink
    -0.38
     linking
    -0.38
    POSITIVE LOGITS
     rounding
    1.16
     Overflow
    0.91
     rounded
    0.89
     decimals
    0.87
     fractional
    0.86
    rounding
    0.86
     precision
    0.86
     Floating
    0.86
     floating
    0.85
     decimal
    0.85
    Act Density 1.366%

    No Known Activations