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

    Neuronpedia

    INDEX
    Explanations

    function definitions in programming or code snippets

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

    def followed by code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.62
     defaultstate
    -0.60
    tonode
    -0.60
     '\\;'
    -0.58
    styleType
    -0.58
    RenderAtEndOf
    -0.56
     AssemblyCulture
    -0.55
    casian
    -0.53
    mobileqq
    -0.50
     الدولى
    -0.49
    POSITIVE LOGITS
     nakalista
    0.49
     voren
    0.41
    IsPostBack
    0.41
    didSet
    0.41
    TagMode
    0.40
    paramMap
    0.39
     cappello
    0.39
    lecular
    0.36
     sayap
    0.35
     réputation
    0.35
    Act Density 0.001%

    No Known Activations