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

    Neuronpedia

    INDEX
    Explanations

    categories and names of food items in a menu

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

    Code snippets and variable assignments

    np_acts-logits-general · gemini-2.0-flash

    sports scores and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    COUVER
    -0.58
     -
    -0.48
     to
    -0.48
     (
    -0.48
     and
    -0.47
    UARIO
    -0.47
     per
    -0.46
    istolet
    -0.45
     –
    -0.45
     re
    -0.45
    POSITIVE LOGITS
     Reſ
    1.17
     Houſe
    1.16
     Majefty
    1.15
     greateſt
    1.11
     pleaſure
    1.08
     Diſ
    1.07
     Efq
    1.06
     Monfieur
    1.05
     Conſ
    1.04
     ſeveral
    1.04
    Act Density 0.357%

    No Known Activations