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

    Neuronpedia

    INDEX
    Explanations

    frequent function words and symbols used in programming and mathematics

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

    academic and technical citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.41
    DIPSETTING
    -0.31
     typelib
    -0.30
     recul
    -0.28
     rire
    -0.27
    円で
    -0.27
     рі
    -0.27
    marvin
    -0.26
    เพ
    -0.26
     frow
    -0.26
    POSITIVE LOGITS
    Personensuche
    0.73
    ScopeManager
    0.69
     مشين
    0.66
     okuyayım
    0.63
    \{\\
    0.62
     ModelExpression
    0.61
    +#+#
    0.61
     EconPapers
    0.61
    RTGC
    0.60
    UnitTesting
    0.60
    Act Density 0.015%

    No Known Activations