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

    Neuronpedia

    INDEX
    Explanations

    instances of code or programming language syntax

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

    code keywords or variables

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects technical, numeric, or math-like tokens (numbers, operators, variables, and other technical/structured code/math tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    tangentMode
    -0.60
    parsedMessage
    -0.59
    ScopeManager
    -0.54
    BufferException
    -0.45
     PDT
    -0.44
     ***!
    -0.43
    はじめに
    -0.43
    機動
    -0.43
     Biôgrafia
    -0.42
    المشاركات
    -0.42
    POSITIVE LOGITS
    LabelTagHelper
    0.59
    MigrationBuilder
    0.48
     ModelExpression
    0.47
    WriteBarrier
    0.47
     TextAppearance
    0.44
     Италијани
    0.43
    SupportActionBar
    0.42
    Enllaços
    0.42
    DockStyle
    0.40
    setVerticalGroup
    0.39
    Act Density 7.570%

    No Known Activations