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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms, specifically those associated with data handling and structure

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colspan
    -0.38
     et
    -0.34
     balancing
    -0.32
    uch
    -0.30
    UnitTesting
    -0.30
     conto
    -0.30
     benefit
    -0.29
    ,
    -0.29
     pass
    -0.29
     balance
    -0.29
    POSITIVE LOGITS
    :✨
    9.38
     autorytatywna
    1.45
    ✨:
    1.28
     EconPapers
    1.17
    SharedCtor
    1.15
     surla
    1.12
    GEBURTSDATUM
    1.11
     للاسماء
    1.09
    Autoritní
    1.09
     nahilalakip
    1.06
    Act Density 0.000%

    No Known Activations