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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their associated verbs in statements

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

    first or last time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overras
    -0.37
     Vielfalt
    -0.37
     citoy
    -0.36
     adicionais
    -0.35
     ferons
    -0.35
     økonom
    -0.34
     hiér
    -0.33
     bonté
    -0.33
     Tatsache
    -0.33
     ninguno
    -0.33
    POSITIVE LOGITS
    posedge
    0.83
    0.82
     Wikimedijinoj
    0.70
    bouts
    0.67
     ویکی‌پدی
    0.67
    getColumnIndex
    0.66
     Sext
    0.65
    fromnode
    0.65
     sext
    0.63
    KommentareTeilen
    0.62
    Act Density 0.024%

    No Known Activations