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

    Neuronpedia

    INDEX
    Explanations

    terms indicating specifics about categories or classifications

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

    special kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.81
    fromnode
    -0.62
     désolés
    -0.61
    +#+
    -0.57
    -0.55
     فريبيس
    -0.54
    ButterKnife
    -0.53
     nakalista
    -0.53
     ویکی‌آمباردا
    -0.52
     Vordergrund
    -0.52
    POSITIVE LOGITS
     speciale
    0.58
     special
    0.58
     осо
    0.57
    特殊的
    0.57
     peculiar
    0.56
     особы
    0.56
    特殊
    0.53
     خاص
    0.53
    独自の
    0.49
     spezielle
    0.48
    Act Density 0.204%

    No Known Activations