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

    Neuronpedia

    INDEX
    Explanations

    markup or structural elements in text

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

    Text following question mark

    np_acts-logits-general · gemini-2.0-flash

    list items and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.86
     purpoſe
    -0.73
    queryInterface
    -0.69
     itſelf
    -0.67
     pleaſure
    -0.67
     Efq
    -0.65
     Chriftian
    -0.64
     légales
    -0.63
     Majefty
    -0.62
     greateſt
    -0.62
    POSITIVE LOGITS
     scrip
    0.58
     cron
    0.54
     autobio
    0.50
     litter
    0.47
     EconPapers
    0.47
     narr
    0.46
    ########.
    0.46
     icon
    0.46
    sketch
    0.44
     script
    0.43
    Act Density 0.066%

    No Known Activations