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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and semicolons

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

    ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.56
     ویکی‌پدی
    -0.56
     فريبيس
    -0.52
     AssemblyCulture
    -0.51
    ఔ
    -0.50
    Билгалдахарш
    -0.49
    InputBorder
    -0.49
     informée
    -0.49
    AsUp
    -0.48
    DeleteBehavior
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.58
    endphp
    0.46
     kasarigan
    0.45
     Freih
    0.44
     てい
    0.43
     Komis
    0.42
     Sebuah
    0.42
     Kommission
    0.42
     Yesus
    0.41
     cuerda
    0.41
    Act Density 0.102%

    No Known Activations