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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence structures

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

    sentence beginnings or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that are numbers or numeric formats (dates, percentages, ranges, decimals) and adjacent technical/mathematical punctuation or symbols (e.g., hyphens, apostrophes, LaTeX markers and subscripts).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    glMatrixMode
    -0.45
     Numerade
    -0.44
     reverse
    -0.44
    verifyException
    -0.44
     Seitz
    -0.43
     '{@
    -0.42
     Jacobsen
    -0.41
    outSlope
    -0.40
     Ruiz
    -0.40
     Eichen
    -0.40
    POSITIVE LOGITS
     Wiktionnaire
    0.44
    ConstraintMaker
    0.43
     старости
    0.41
     виправивши
    0.40
     MainAxisSize
    0.40
    ſelves
    0.38
     ***!
    0.36
    KommentareTeilen
    0.36
    {`
    0.35
    ':
    0.35
    Act Density 0.573%

    No Known Activations