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

    Neuronpedia

    INDEX
    Explanations

    keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verdens
    0.44
     آف
    0.43
     calendriers
    0.41
     recompens
    0.41
    Stories
    0.40
    Routes
    0.40
    SOUR
    0.38
    URCH
    0.38
     changements
    0.38
    Smile
    0.38
    POSITIVE LOGITS
     keywords
    1.91
    keywords
    1.59
     Keywords
    1.56
    Keywords
    1.55
    关键词
    1.46
     keyword
    1.45
    キーワード
    1.43
    关键字
    1.38
    keyword
    1.23
    Keyword
    1.23
    Act Density 0.045%

    No Known Activations