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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters used in code structures

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

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cappello
    -0.57
     giusti
    -0.57
     nivå
    -0.52
     المعيارى
    -0.50
     esprits
    -0.48
     giudizio
    -0.47
     riuscito
    -0.47
     élevés
    -0.46
     väx
    -0.46
    madu
    -0.45
    POSITIVE LOGITS
    setVerticalGroup
    0.79
    MigrationBuilder
    0.76
    posedge
    0.70
    出版年
    0.66
     nakalista
    0.63
    Chham
    0.62
    hamdu
    0.60
     Roskov
    0.60
    PutMapping
    0.59
    jsxFileName
    0.58
    Act Density 0.037%

    No Known Activations