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

    Neuronpedia

    INDEX
    Explanations

    instances of significant emphasis or strong statements within a text

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

    math, code, and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.52
    XmlAccessType
    -0.51
     ModelExpression
    -0.45
    LabelTagHelper
    -0.43
    sizeCache
    -0.41
    setupUi
    -0.41
     урна
    -0.39
     Gin
    -0.38
    PostMapping
    -0.37
     Signalez
    -0.37
    POSITIVE LOGITS
     IFTT
    0.57
     EconPapers
    0.56
     NSCoder
    0.52
     venganza
    0.52
     negociación
    0.52
    Bibliograf
    0.50
    EDEFAULT
    0.49
     AssemblyCulture
    0.49
    autique
    0.49
    gelopen
    0.48
    Act Density 0.059%

    No Known Activations