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

    Neuronpedia

    INDEX
    Explanations

    elements of code related to undefined or special functionality

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

    Tokens preceding specific double underscore patterns

    np_acts-logits-general · gemini-2.0-flash

    `__` prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -1.08
     propOrder
    -1.00
    parsedMessage
    -0.95
     ComVisible
    -0.90
     SwitchCompat
    -0.88
    MigrationBuilder
    -0.86
    Vidite
    -0.85
    FunctionFlags
    -0.84
    DockStyle
    -0.84
    примеча
    -0.83
    POSITIVE LOGITS
    (__
    1.39
     __
    1.32
     (__
    1.31
     (!__
    1.29
    ->__
    1.23
    /__
    1.17
    #__
    1.11
    &__
    1.10
    .__
    1.05
    ("__
    1.05
    Act Density 0.095%

    No Known Activations