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

    Neuronpedia

    INDEX
    Explanations

    Hong Kong and Cantonese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鳟
    0.71
    Ohio
    0.71
     Ohio
    0.69
    炝
    0.62
    Nashville
    0.60
     Saginaw
    0.59
    烀
    0.59
    Oklahoma
    0.58
    疖
    0.58
    狍
    0.57
    POSITIVE LOGITS
     Hong
    2.16
     HK
    2.00
    Hong
    1.97
     Hongkong
    1.95
    香港
    1.91
     Kowloon
    1.76
    HK
    1.70
     Cantonese
    1.66
     hong
    1.63
     hk
    1.59
    Act Density 0.024%

    No Known Activations