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

    Neuronpedia

    INDEX
    Explanations

    battle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    之道
    -0.08
    趁
    -0.07
    每一个人
    -0.07
    alive
    -0.07
     Verse
    -0.07
    (stats
    -0.07
     Portuguese
    -0.06
    用餐
    -0.06
    焉
    -0.06
    如果不是
    -0.06
    POSITIVE LOGITS
    _sequence
    0.07
     },{
    0.07
    摆
    0.07
    _dem
    0.06
     circulated
    0.06
    生产的
    0.06
     projectId
    0.06
     ")
    0.06
     oper
    0.06
    "],["
    0.06
    Act Density 0.007%

    No Known Activations