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

    Neuronpedia

    INDEX
    Explanations

    Java class definitions and their extensions

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

    GUI code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.68
     فريبيس
    -0.59
     surla
    -0.59
    RTHOOK
    -0.58
    🇶
    -0.57
    elemField
    -0.56
     betweenstory
    -0.54
     ویکی‌پدی
    -0.54
     EconPapers
    -0.54
     समीक्षाएं
    -0.51
    POSITIVE LOGITS
    JFrame
    0.55
     JFrame
    0.46
     QWidget
    0.44
    JPanel
    0.43
    QWidget
    0.42
    AccessFile
    0.40
     JPanel
    0.39
    GeneratedMessage
    0.38
     Fre
    0.35
     prawa
    0.35
    Act Density 0.003%

    No Known Activations