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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to specific dates or publications

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

    companies based

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.76
    Билгалдахарш
    -0.75
    
    -0.72
     <=",
    -0.70
    DoubleQuotes
    -0.66
     BorderRadius
    -0.65
     ModelExpression
    -0.65
     للمعارف
    -0.62
     Normdatei
    -0.62
    InjectAttribute
    -0.60
    POSITIVE LOGITS
    </caption>
    0.55
    ITest
    0.48
    ⋮
    0.48
    lardır
    0.48
     aſ
    0.48
     alſo
    0.47
    řeb
    0.46
     sonore
    0.46
     Reſ
    0.45
    atric
    0.45
    Act Density 0.204%

    No Known Activations