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

    Neuronpedia

    INDEX
    Explanations

    lists non-English characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sich
    0.51
     kristall
    0.48
     Productivity
    0.47
    crystall
    0.47
    ޗ
    0.47
     Durchschnitt
    0.47
     Wurzel
    0.46
     Camus
    0.46
    arlin
    0.46
    vila
    0.46
    POSITIVE LOGITS
    et
    0.53
     scandals
    0.43
    ち
    0.43
    随机
    0.41
    ０
    0.40
    郁
    0.40
    马上
    0.39
    ளால்
    0.39
     lawsuit
    0.38
     yık
    0.38
    Act Density 0.000%

    No Known Activations