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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements commonly used in coding or markup languages

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

    % placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.47
     ویکی‌پدیا
    -0.43
    出版年
    -0.41
     BoxDecoration
    -0.39
     صوتيه
    -0.39
    adaptiveStyles
    -0.39
    parsedMessage
    -0.38
    crollView
    -0.38
     jūs
    -0.37
    PMailer
    -0.37
    POSITIVE LOGITS
    0.63
     
    0.49
     kasarigan
    0.48
     queſta
    0.47
    intios
    0.47
    PathVariable
    0.47
    bastien
    0.46
    Filmografie
    0.46
    StructEnd
    0.45
    Pois
    0.45
    Act Density 0.166%

    No Known Activations