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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax elements and symbols

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

    formatting and separators

    np_acts-logits-general · gemini-2.5-flash-lite

    document-structure markers—section headings, titles, and other formatting or metadata tokens that signal structural boundaries.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     незавершена
    -0.93
     وتسجيلات
    -0.90
    UrlResolution
    -0.90
     CreateTagHelper
    -0.77
    +#+
    -0.75
     Мексичка
    -0.70
     فريبيس
    -0.70
    archiviato
    -0.69
     Chwiliwch
    -0.68
    httphttps
    -0.68
    POSITIVE LOGITS
     betweenstory
    0.40
    ⤹
    0.33
     faſt
    0.30
    endregion
    0.27
     gata
    0.26
    ropriate
    0.25
    calipsis
    0.23
    <sup>
    0.23
     laver
    0.22
     escar
    0.22
    Act Density 0.004%

    No Known Activations