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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to promotions and offers

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

    numbers and "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ăsp
    -0.34
    iseite
    -0.34
     Cuatro
    -0.32
    fördert
    -0.32
     French
    -0.32
     yder
    -0.31
    iertamente
    -0.31
     Northwestern
    -0.30
    urismo
    -0.29
    equiv
    -0.29
    POSITIVE LOGITS
    AnchorStyles
    0.66
     CreateTagHelper
    0.63
     surla
    0.59
    Tikang
    0.57
    منابع
    0.54
    KommentareTeilen
    0.52
    󠁴
    0.51
    RegressionTest
    0.50
     EconPapers
    0.50
     ویکی‌پدیای
    0.50
    Act Density 0.087%

    No Known Activations