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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significant changes or impacts

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

    Non-English Wikipedia or dictionary entries

    np_acts-logits-general · gemini-2.0-flash

    references and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.62
     Normdatei
    -0.53
    kmäler
    -0.47
    taminophen
    -0.46
     ModelExpression
    -0.46
     nakalista
    -0.46
     Majefty
    -0.45
     AspNetCore
    -0.45
     linkovi
    -0.44
    ssaint
    -0.44
    POSITIVE LOGITS
     مشين
    0.46
    verwijspagina
    0.43
    SEGUIR
    0.43
     Wiktionnaire
    0.42
    Билгалдахарш
    0.41
     referrerpolicy
    0.40
     surla
    0.37
     Prior
    0.37
    Prior
    0.37
     Underlying
    0.36
    Act Density 0.254%

    No Known Activations