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

    Neuronpedia

    INDEX
    Explanations

    Chinese words and location names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鲔
    0.90
    堊
    0.82
    鏻
    0.77
    鳟
    0.75
    Benzyl
    0.74
    Methylsulfanyl
    0.74
    硖
    0.74
    爌
    0.74
    蓣
    0.74
    禣
    0.74
    POSITIVE LOGITS
     Chinese
    1.09
     chinese
    0.96
     yuan
    0.91
     चीन
    0.90
     zhong
    0.89
     China
    0.89
     Beijing
    0.89
     WeChat
    0.89
     Shanghai
    0.88
     Chengdu
    0.87
    Act Density 0.030%

    No Known Activations