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

    Neuronpedia

    INDEX
    Explanations

    mentions of large sums of money, specifically in billions and trillions

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

    numerical quantities and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.80
     resourceCulture
    -0.75
    HtmlAttribute
    -0.69
    OGND
    -0.67
     հղումներ
    -0.64
    TagMode
    -0.58
     ujednoznacz
    -0.58
     فريبيس
    -0.56
    IntoConstraints
    -0.56
    цездатний
    -0.56
    POSITIVE LOGITS
     triliun
    0.46
     spreken
    0.39
     úrov
    0.36
     mulia
    0.36
     gavetas
    0.35
     luzes
    0.35
     settimane
    0.33
     Beobachtung
    0.32
     membunuh
    0.32
     hadapan
    0.32
    Act Density 0.055%

    No Known Activations