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

    Neuronpedia

    INDEX
    Explanations

    references to statistical analysis and results in research studies

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

    Negative numbers, decimals, or symbols

    np_acts-logits-general · gemini-2.0-flash

    numeric values and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     հղումներ
    -0.62
    kreis
    -0.50
    KommentareTeilen
    -0.47
     etc
    -0.46
    كذا
    -0.45
     plant
    -0.44
    __*/
    -0.44
     us
    -0.43
     sino
    -0.43
    mpä
    -0.43
    POSITIVE LOGITS
     فريبيس
    0.84
     Normdatei
    0.75
    tvguidetime
    0.72
    abestanden
    0.66
    IsContent
    0.65
    TagMode
    0.64
    twimg
    0.64
     مرئيه
    0.64
     <",
    0.63
    0.63
    Act Density 1.034%

    No Known Activations