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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in texts

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

    times, dates, or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.47
    раздо
    -0.46
     verlie
    -0.44
     veiligheid
    -0.43
     daarvan
    -0.41
    IntoConstraints
    -0.40
     المعيارى
    -0.39
     penyebab
    -0.39
     ویکی‌پدی
    -0.39
    bedaan
    -0.38
    POSITIVE LOGITS
     ujednoznacz
    0.54
    Brief
    0.50
     adjour
    0.48
     Conven
    0.46
    ⟬
    0.46
     Enrichment
    0.45
    发表于
    0.45
     Brief
    0.45
    Diweddarwch
    0.45
     conven
    0.45
    Act Density 0.013%

    No Known Activations