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

    Neuronpedia

    INDEX
    Explanations

    structured lists or enumerated items

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

    listing numbers, items, or lessons

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

    This neuron detects numeric list or section markers — standalone digits (and adjacent punctuation) used to enumerate items, paragraphs, or sections.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.82
    modelBuilder
    -0.60
     يتيمه
    -0.59
    GEBURTSDATUM
    -0.57
     propOrder
    -0.56
    FieldBuilder
    -0.55
     мәкал
    -0.54
    ondissement
    -0.54
    MemoryWarning
    -0.54
    AccessorTable
    -0.52
    POSITIVE LOGITS
     تضيفلها
    0.39
     enfans
    0.35
     Bewußt
    0.35
     leçon
    0.34
     giebt
    0.33
     vnto
    0.31
     żyw
    0.30
     dziennik
    0.30
     vérit
    0.30
    ########.
    0.30
    Act Density 0.119%

    No Known Activations