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

    Neuronpedia

    INDEX
    Explanations

    consciousness

    np_acts-logits-general · gemini-2.5-flash-lite

    spots Chinese abstract/technical nouns—especially ideological, philosophical or academic topic words (e.g., terms about consciousness, schools of thought, political/educational concepts).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     full
    0.45
    骓
    0.41
     notice
    0.39
     cruise
    0.39
    ocode
    0.39
     revoked
    0.39
     large
    0.39
     cruises
    0.38
     limitless
    0.38
     revoke
    0.38
    POSITIVE LOGITS
    形態
    0.52
    葉
    0.46
    叶
    0.43
    形态
    0.43
    leaf
    0.42
    ult
    0.41
    Ult
    0.38
     Ult
    0.38
    分子
    0.38
    淡
    0.38
    Act Density 0.013%

    No Known Activations