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

    Neuronpedia

    INDEX
    Explanations

    references to interactions with online content and subscriptions

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

    given a/the/one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estacks
    -0.35
     Preferencias
    -0.33
    em
    -0.32
    ingdon
    -0.31
    pul
    -0.30
    uer
    -0.29
    rad
    -0.29
    uben
    -0.29
    lei
    -0.28
    amas
    -0.28
    POSITIVE LOGITS
    ########.
    0.69
     ProtoMessage
    0.69
    出版年
    0.60
    PreInfinity
    0.59
     AssemblyCulture
    0.57
    exitRule
    0.57
     coraggio
    0.55
    ReusableCell
    0.54
    Tembelea
    0.54
     vermelhas
    0.53
    Act Density 0.042%

    No Known Activations