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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in programming or scripting syntax

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

    "as" followed by a symbol

    np_acts-logits-general · gemini-2.0-flash

    quantities, code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的意思
    -0.49
    signol
    -0.44
     "";
    -0.43
    зова
    -0.42
    口
    -0.42
    ակ
    -0.42
    lies
    -0.41
     до
    -0.41
    陶
    -0.41
    jeno
    -0.41
    POSITIVE LOGITS
    BufferException
    0.85
    AccessorTable
    0.76
    MigrationBuilder
    0.70
     مشين
    0.69
    IsContent
    0.69
    [++
    0.68
     asmen
    0.67
     varandra
    0.67
    enumi
    0.66
     propOrder
    0.65
    Act Density 0.019%

    No Known Activations