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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology and references to theorems or lemmas in formal proofs

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

    Mathematical lemmas, theorems, and facts

    np_acts-logits-general · gemini-2.0-flash

    citations to lemmas and theorems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.66
    ActionCreators
    -0.61
    TintMode
    -0.60
    ViewImports
    -0.60
    principalTable
    -0.60
     بيها
    -0.59
    WriteBarrier
    -0.58
    FieldBuilder
    -0.58
    MigrationBuilder
    -0.58
    RunWith
    -0.57
    POSITIVE LOGITS
     properties
    0.76
     property
    0.73
     theorem
    0.73
     rule
    0.70
    properties
    0.67
     law
    0.66
    property
    0.65
    Property
    0.63
     teore
    0.63
     principle
    0.63
    Act Density 1.162%

    No Known Activations