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

    Neuronpedia

    INDEX
    Explanations

    percentages related to various subjects

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

    Percentage or fraction "of"

    np_acts-logits-general · gemini-2.0-flash

    percentages followed by categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.45
    thâu
    -0.40
    äuser
    -0.39
    unción
    -0.38
    ChrTalk
    -0.36
     berdiri
    -0.35
    padek
    -0.35
    ologico
    -0.35
     оказа
    -0.35
    behaviour
    -0.35
    POSITIVE LOGITS
    parsedMessage
    0.61
    GEBURTSDATUM
    0.59
     EconPapers
    0.59
    BufferException
    0.54
    WebServlet
    0.52
    MigrationBuilder
    0.52
    InputBorder
    0.50
     total
    0.48
    RenderAtEndOf
    0.47
    TypedDataSet
    0.47
    Act Density 0.380%

    No Known Activations