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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the structure and flow of context in written communication

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

    sentence start, conjunctions, or context markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    formatter
    -0.36
    GTCX
    -0.35
    ἶ
    -0.34
     intersection
    -0.34
     …
    -0.33
     Bell
    -0.33
    AntiForgeryToken
    -0.33
    eado
    -0.33
     Bes
    -0.33
    AddTagHelper
    -0.32
    POSITIVE LOGITS
    iastes
    0.50
    Personensuche
    0.50
     ویکی‌پدی
    0.49
    TagMode
    0.49
    تقاوى
    0.49
     titolata
    0.47
    SequentialGroup
    0.47
    richTextPanel
    0.44
    setViewportView
    0.43
     circonst
    0.43
    Act Density 0.095%

    No Known Activations