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

    Neuronpedia

    INDEX
    Explanations

    unusual punctuation marks and dialogue tags

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

    quotation marks and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     option
    -0.40
    InitVars
    -0.36
    srcs
    -0.35
     inz
    -0.35
    สุข
    -0.35
    <>();
    -0.35
    BarItem
    -0.34
     bib
    -0.33
     Sup
    -0.33
     nucleotides
    -0.33
    POSITIVE LOGITS
     ModelExpression
    0.60
     <<<<<<<<<<<<<<
    0.59
     nahilalakip
    0.58
    AnimationsModule
    0.54
    الحياه
    0.52
    RenderAtEndOf
    0.50
    fromnode
    0.49
     continúas
    0.47
    ValueStyle
    0.47
    Vorlage
    0.46
    Act Density 0.388%

    No Known Activations