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

    Neuronpedia

    INDEX
    Explanations

    korean language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    （
    0.54
     Osaka
    0.51
     Hokkaido
    0.50
     kawaii
    0.50
    料理
    0.49
     anime
    0.49
     Япо
    0.48
     は
    0.48
     Hakone
    0.48
    Anime
    0.48
    POSITIVE LOGITS
     korean
    0.80
     korea
    0.77
    韓國
    0.71
    韩国
    0.71
     Korea
    0.70
     Korean
    0.67
    Korean
    0.67
    Korea
    0.65
    ₩
    0.61
    삼성
    0.61
    Act Density 0.002%

    No Known Activations