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

    Neuronpedia

    INDEX
    Explanations

    specific legal or technical terms and their implications

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

    or [action/state/item]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.45
    HomeAsUpEnabled
    -0.44
    +#+
    -0.42
     olvidar
    -0.42
     arşivlendi
    -0.41
     inext
    -0.41
     Füßen
    -0.41
     forgets
    -0.40
     مشين
    -0.40
     kartun
    -0.39
    POSITIVE LOGITS
    RefNanny
    0.56
    انيف
    0.55
     transférez
    0.49
     <>",
    0.49
    complexContent
    0.48
     désolés
    0.47
    minecraftforge
    0.47
    itinéraire
    0.45
    ">//
    0.44
    mentaux
    0.44
    Act Density 0.002%

    No Known Activations