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

    Neuronpedia

    INDEX
    Explanations

    double-check and verify information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ების
    0.76
    庖
    0.72
    ített
    0.72
     rimu
    0.70
    iunea
    0.70
     पौधे
    0.69
     सिले
    0.69
    ife
    0.68
     menghilangkan
    0.67
     tracksuit
    0.67
    POSITIVE LOGITS
     win
    0.76
    win
    0.72
     Win
    0.66
    Win
    0.65
    AGENT
    0.62
     WIN
    0.61
    展開
    0.56
    まれ
    0.56
    爆发
    0.56
    agent
    0.55
    Act Density 0.094%

    No Known Activations