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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates or numerical identifiers in text

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

    date, citations, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estacks
    -0.34
    Zdroje
    -0.32
     مؤرشف
    -0.30
     Италијани
    -0.30
     Administrativna
    -0.30
     ngoài
    -0.29
    TypedDataSet
    -0.28
    대로
    -0.28
    PENDAHULUAN
    -0.27
    basicConfig
    -0.27
    POSITIVE LOGITS
    majánló
    0.68
    琑
    0.56
     vooz
    0.56
     للاسماء
    0.55
     HasFactory
    0.54
    lccn
    0.54
    Diweddarwch
    0.53
    𑄮
    0.53
    BeginInit
    0.52
    talt
    0.52
    Act Density 0.370%

    No Known Activations