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

    Neuronpedia

    INDEX
    Explanations

    references to subscription and publication actions in a programming context

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

    programming keywords and dialogue turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.62
    ViewImports
    -0.54
    interopRequire
    -0.50
    #+#
    -0.47
     ModelExpression
    -0.45
    ConstraintMaker
    -0.44
    expandindo
    -0.44
    homonymie
    -0.43
     educativas
    -0.42
     kasarigan
    -0.42
    POSITIVE LOGITS
     légales
    0.36
     Subscribers
    0.36
    AsNil
    0.36
    blatt
    0.35
     légale
    0.35
    Filmografie
    0.35
    vér
    0.35
     Saran
    0.35
     Spitz
    0.34
     reten
    0.34
    Act Density 0.003%

    No Known Activations