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

    Neuronpedia

    INDEX
    Explanations

    terms related to various contexts of heaviness or significant weight

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

    heavy descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.75
    ptonshire
    -0.70
    المناصب
    -0.69
    afficheront
    -0.68
    帖最后由
    -0.67
     Paglinawan
    -0.67
     StatelessWidget
    -0.65
    parsedMessage
    -0.65
    Geplaatst
    -0.64
    ロウィン
    -0.64
    POSITIVE LOGITS
     heavy
    1.73
    Heavy
    1.62
     Heavy
    1.60
    heavy
    1.59
     HEAVY
    1.52
     heaviest
    1.35
     heavier
    1.32
     pesados
    1.25
     pesada
    1.21
     pesado
    1.20
    Act Density 0.019%

    No Known Activations