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

    Neuronpedia

    INDEX
    Explanations

    playing a game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    に
    0.92
    ৭
    0.90
    에
    0.81
    嵬
    0.73
    us
    0.73
    ामध्ये
    0.72
     اولیه
    0.72
    oč
    0.71
    的他
    0.70
    in
    0.68
    POSITIVE LOGITS
     and
    0.88
    ند
    0.83
     games
    0.82
    ص
    0.76
    ل
    0.72
     by
    0.71
     игры
    0.70
     on
    0.70
    نا
    0.69
     oyun
    0.69
    Act Density 0.038%

    No Known Activations