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

    Neuronpedia

    INDEX
    Explanations

    programming language keywords and constructs related to function definitions and access modifiers

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

    Variable declarations and type annotations

    np_acts-logits-general · gemini-2.0-flash

    programming code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.65
    AutoScaleMode
    -0.52
    ]^{-
    -0.50
     ust
    -0.47
    wpi
    -0.47
     ${
    -0.46
    MigrationBuilder
    -0.45
    asion
    -0.44
    گذ
    -0.44
    ]^{\
    -0.44
    POSITIVE LOGITS
    final
    1.05
    late
    0.98
    bool
    0.91
     final
    0.90
    Future
    0.90
    void
    0.86
     Future
    0.77
     late
    0.77
     bool
    0.77
    String
    0.74
    Act Density 0.040%

    No Known Activations