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

    Neuronpedia

    INDEX
    Explanations

    technical terms and expressions related to programming and data

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

    Code or mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    measured outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.68
     ostavi
    -0.65
     ModelExpression
    -0.64
     بيها
    -0.63
     تكبرها
    -0.62
    المناصب
    -0.61
     typelib
    -0.60
    writeField
    -0.57
    migrationBuilder
    -0.55
    LLocation
    -0.55
    POSITIVE LOGITS
    󠁴
    0.69
    ArrowToggle
    0.57
     Италијани
    0.53
    fromnode
    0.50
    SourceChecksum
    0.48
     ExecuteAsync
    0.48
    HideFlags
    0.44
    elemField
    0.41
     subterrá
    0.40
    SuspendLayout
    0.40
    Act Density 1.050%

    No Known Activations