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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance and support for visitors or users in an online context

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

    space suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pra
    -0.46
    Tracce
    -0.45
    Pra
    -0.44
     ſta
    -0.43
     Lat
    -0.43
     DIC
    -0.42
    ListResponse
    -0.41
     ſte
    -0.41
     Won
    -0.41
     Diſ
    -0.40
    POSITIVE LOGITS
     ویکی‌پدی
    0.49
     Grüsse
    0.48
    лтемелер
    0.48
     ostavi
    0.48
    UnusedPrivate
    0.47
     asesinado
    0.47
    unknownFields
    0.46
     Autorin
    0.46
     NSCoder
    0.46
    routeProvider
    0.46
    Act Density 0.347%

    No Known Activations