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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and spacing patterns between words

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

    number or punctuation followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     schermata
    -0.38
    ranath
    -0.36
     conventional
    -0.35
     гру
    -0.35
     turn
    -0.35
    fully
    -0.35
     extranjera
    -0.35
     @"/
    -0.34
    ⤹
    -0.34
     optical
    -0.32
    POSITIVE LOGITS
    MigrationBuilder
    0.88
    tangentMode
    0.64
     Wicidata
    0.60
    ьаж
    0.58
     ویکی‌پدی
    0.56
    XmlAccessorType
    0.54
    الدراسه
    0.54
    #+#
    0.54
    findpost
    0.54
     verwijzen
    0.53
    Act Density 0.006%

    No Known Activations