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

    Neuronpedia

    INDEX
    Explanations

    references to types of scientific or technical notations and their components

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

    Code, symbols, and specialized terminology

    np_acts-logits-general · gemini-2.0-flash

    code artifacts and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     has
    -0.61
     itself
    -0.57
     have
    -0.57
     will
    -0.56
     was
    -0.55
     so
    -0.54
     is
    -0.53
     in
    -0.53
    ?
    -0.51
     over
    -0.51
    POSITIVE LOGITS
    rrggbb
    1.03
    UnusedPrivate
    1.01
    WebVitals
    0.97
     AttributeSet
    0.95
     Majefty
    0.95
    ArrowToggle
    0.94
    makeConstraints
    0.91
     بيها
    0.91
    AsUp
    0.90
    Personendaten
    0.88
    Act Density 0.710%

    No Known Activations