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

    Neuronpedia

    INDEX
    Explanations

    outperformed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    彼は
    0.45
    巩
    0.45
    spirator
    0.44
    unächst
    0.43
    他在
    0.42
    他的
    0.42
     hänen
    0.41
     परिमेय
    0.40
    គាត់
    0.40
    ذج
    0.39
    POSITIVE LOGITS
     outre
    0.82
    Out
    0.67
     Out
    0.60
     OUT
    0.59
     outperformed
    0.59
     outp
    0.57
    OUT
    0.56
     outnumbered
    0.55
     outweigh
    0.54
     out
    0.54
    Act Density 0.002%

    No Known Activations