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

    Neuronpedia

    INDEX
    Explanations

    punctuation and delimiters in the text

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

    programming types and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iArr
    -0.41
     tận
    -0.37
    即
    -0.35
    annten
    -0.33
    Varint
    -0.33
    
    -0.31
    —¡
    -0.31
     نو
    -0.31
    конец
    -0.31
     AssemblyProduct
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.77
    ⓧ
    0.68
    LookAnd
    0.67
    :✨
    0.62
    Lähteet
    0.57
    $_['
    0.57
     ModelExpression
    0.56
     TextAppearance
    0.54
     يتيمه
    0.52
    出版年
    0.52
    Act Density 0.015%

    No Known Activations