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

    Neuronpedia

    INDEX
    Explanations

    speculative or uncertain language regarding events and conditions

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

    words of likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.49
     juſ
    -0.48
    Hozzáférés
    -0.48
     Besøkt
    -0.47
     raiſ
    -0.46
    runApp
    -0.45
     faſt
    -0.45
    :][
    -0.43
     Theſe
    -0.42
    balleur
    -0.41
    POSITIVE LOGITS
     likely
    0.43
    likely
    0.43
     kemungkinan
    0.43
    Likely
    0.42
     disambiguazione
    0.42
    Possibly
    0.41
    ínű
    0.39
     Likely
    0.38
     disponibilités
    0.37
    Probably
    0.36
    Act Density 0.509%

    No Known Activations