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

    Neuronpedia

    INDEX
    Explanations

    references to sections and steps in a structured document

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

    document structure headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.52
    UnsafeEnabled
    -0.48
    cookieParser
    -0.46
     EconPapers
    -0.46
    mergeFrom
    -0.43
     Comprometido
    -0.43
     silicona
    -0.43
     ComVisible
    -0.42
     pstmt
    -0.41
     calendriers
    -0.40
    POSITIVE LOGITS
    vella
    0.44
    第一章
    0.44
    টি
    0.43
    Yesterday
    0.42
    glie
    0.41
    fucker
    0.41
    Col
    0.41
    #
    0.41
    denly
    0.41
     gug
    0.40
    Act Density 0.103%

    No Known Activations