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

    Neuronpedia

    INDEX
    Explanations

    articles such as "a" and "an" in text

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

    a X or a Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.38
    COUVER
    -0.37
    Pest
    -0.37
     yii
    -0.36
    きましたが
    -0.36
     onAnimation
    -0.35
    ましたが
    -0.35
    Isra
    -0.35
     not
    -0.35
     perhaps
    -0.35
    POSITIVE LOGITS
    Portail
    0.63
     חיצוניים
    0.58
    󠁢
    0.55
    ########.
    0.53
     فريبيس
    0.51
    MLLoader
    0.48
    kuuta
    0.47
     opérés
    0.47
    Begriffsklä
    0.46
     ibunya
    0.45
    Act Density 0.101%

    No Known Activations