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

    Neuronpedia

    INDEX
    Explanations

    numbers after chess moves or card ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    該当
    0.97
    ಟ್‌
    0.86
    }_{+}\
    0.86
    有多少
    0.83
    ディー
    0.81
    І
    0.81
    ضی
    0.80
     ধনী
    0.79
    ้อมูล
    0.79
    団体
    0.79
    POSITIVE LOGITS
     movilidad
    1.03
     tabuleiro
    0.96
     brooding
    0.94
    7
    0.93
    chim
    0.93
     acciaio
    0.93
    analyze
    0.93
     chess
    0.92
     viagem
    0.92
     hierro
    0.90
    Act Density 0.211%

    No Known Activations