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

    Neuronpedia

    INDEX
    Explanations

    numeric data related to statistical analysis, particularly percentages and counts

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

    Numeric ranges or intervals

    np_acts-logits-general · gemini-2.0-flash

    scores and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     even
    -0.48
     before
    -0.48
     ver
    -0.43
     rather
    -0.41
     ve
    -0.40
     Z
    -0.40
     trước
    -0.40
     how
    -0.40
     carré
    -0.39
    까지
    -0.39
    POSITIVE LOGITS
    ThroughAttribute
    0.97
     Daarna
    0.92
    TypedDataSet
    0.88
    NameInMap
    0.88
    WriteBarrier
    0.87
    addCriterion
    0.86
    oredCriteria
    0.85
    FunctionFlags
    0.85
    MigrationBuilder
    0.82
     pleaſure
    0.81
    Act Density 0.369%

    No Known Activations