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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and their attributes in a structured format, often associated with categories or classifications

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

    hyphenated words or mathematical operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.34
     chimiques
    -0.33
     químicos
    -0.32
     fotografico
    -0.29
     mystère
    -0.28
     ujednoznacz
    -0.27
     económicos
    -0.27
     Église
    -0.27
    putString
    -0.26
     económicas
    -0.26
    POSITIVE LOGITS
     Audiodateien
    0.60
     >=",
    0.58
    LookAnd
    0.58
     nahilalakip
    0.54
     للاسماء
    0.53
    0.53
    DoubleQuotes
    0.52
    ьаж
    0.52
    Personensuche
    0.52
    期刊论文
    0.52
    Act Density 0.089%

    No Known Activations