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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of specific determiners and quantifiers

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

    Text fragments preceding a question mark

    np_acts-logits-general · gemini-2.0-flash

    categories and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.63
    twimg
    -0.59
     tantas
    -0.56
     оригіналу
    -0.55
     nawr
    -0.53
    imanapun
    -0.50
    voorbeeld
    -0.49
    SharedDtor
    -0.48
     vrai
    -0.48
     tantos
    -0.47
    POSITIVE LOGITS
     category
    0.82
     month
    0.68
    agory
    0.64
    XmlAccessType
    0.61
     concept
    0.61
     modalidad
    0.60
     categoría
    0.59
     province
    0.58
     area
    0.58
     aspect
    0.57
    Act Density 0.544%

    No Known Activations