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

    Neuronpedia

    INDEX
    Explanations

    the presence of whitespace characters or formatting elements

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

    medical records and scientific data

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

    the neuron detects numerical tokens and numeric/measurement references (e.g., measurements, years, table/figure/table-number labels).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    怪
    -0.33
     officiers
    -0.33
    COORD
    -0.30
     solas
    -0.30
    uhnya
    -0.30
    corporated
    -0.29
     diu
    -0.29
    ьи
    -0.29
     bota
    -0.29
     designated
    -0.29
    POSITIVE LOGITS
     disambiguazione
    0.73
    adaptiveStyles
    0.59
    getWriter
    0.57
    oredCriteria
    0.57
     Geſch
    0.56
    parsedMessage
    0.56
     Lightboxes
    0.56
    dafx
    0.55
     NSCoder
    0.55
     EconPapers
    0.54
    Act Density 0.787%

    No Known Activations