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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the introduction or categorization of a class or type of entity

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

    class of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.52
     wikipagina
    -0.47
     Wikiseite
    -0.45
    StoreMessageInfo
    -0.45
    PYX
    -0.43
     pinulongan
    -0.43
    ModelMap
    -0.42
     Pergamon
    -0.41
    Slf
    -0.41
     noDo
    -0.40
    POSITIVE LOGITS
    rungsseite
    0.47
     HasFactory
    0.43
     ujednoznacz
    0.41
    ppuden
    0.41
    Referanser
    0.40
     Picchu
    0.39
    0.39
    一群
    0.38
     disambiguazione
    0.38
    classes
    0.38
    Act Density 0.096%

    No Known Activations