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

    Neuronpedia

    INDEX
    Explanations

    sections of code or text that indicate closures or endings, especially pertaining to blocks structured by curly braces

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

    programming code and diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.52
    Билгалдахарш
    -0.44
     CURIAM
    -0.42
    gjenge
    -0.42
    riever
    -0.40
    typeorm
    -0.40
     coti
    -0.38
    趨
    -0.37
    adalajara
    -0.37
     SwitchCompat
    -0.36
    POSITIVE LOGITS
    uxxxx
    0.69
    ="@+
    0.61
    Tembelea
    0.61
     tartalomajánló
    0.60
    OuterAlt
    0.56
    НИК
    0.54
     GenerationType
    0.53
    TokenNameLPAREN
    0.52
    HXLINE
    0.48
     てい
    0.47
    Act Density 0.018%

    No Known Activations