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

    Neuronpedia

    INDEX
    Explanations

    Chinese apps and tech terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PFAS
    0.82
    堊
    0.77
    啮
    0.76
    銠
    0.74
    睪
    0.74
    鰓
    0.72
    鳟
    0.72
    Complexity
    0.69
     анато
    0.69
    缟
    0.67
    POSITIVE LOGITS
    weixin
    0.77
     kua
    0.76
    手机
    0.72
    zhang
    0.71
     mall
    0.71
    baidu
    0.71
     jie
    0.70
    zhong
    0.70
     hong
    0.69
     Chinese
    0.69
    Act Density 0.016%

    No Known Activations