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

    Neuronpedia

    INDEX
    Explanations

    we believe or we do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     garrison
    0.42
    即可
    0.41
     Wins
    0.38
     quasi
    0.37
     Torque
    0.37
     Rave
    0.37
    earance
    0.36
     выходит
    0.36
     tf
    0.36
     Notably
    0.36
    POSITIVE LOGITS
     আমরা
    0.85
     we
    0.83
     мы
    0.80
     เรา
    0.77
    我们
    0.77
    我們
    0.76
     creemos
    0.73
     हमने
    0.72
     我们
    0.71
     אנחנו
    0.71
    Act Density 0.011%

    No Known Activations