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

    Neuronpedia

    INDEX
    Explanations

    spaces or whitespace characters within a document

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

    Follows numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    Davis, Grape, Successful, KY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -1.35
     tartalomajánló
    -1.24
     Roskov
    -1.23
     estekak
    -1.13
    WebElementEntity
    -0.98
     ویکی‌پدی
    -0.95
     AssemblyVersion
    -0.94
     Paglinawan
    -0.93
    OGND
    -0.91
    GEBURTSDATUM
    -0.90
    POSITIVE LOGITS
     Saltar
    0.52
    aderie
    0.44
     POC
    0.40
    laze
    0.39
     Red
    0.38
     آنجا
    0.38
     itemprop
    0.38
     soft
    0.38
    <h6>
    0.37
    Red
    0.37
    Act Density 0.231%

    No Known Activations