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

    Neuronpedia

    INDEX
    Explanations

    declared independence and won

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alguém
    0.49
     iemand
    0.48
     alguien
    0.47
     jemand
    0.46
     რომელი
    0.43
     someone
    0.43
    某个
    0.43
    Someone
    0.42
    someone
    0.42
    হারা
    0.41
    POSITIVE LOGITS
     impressively
    0.65
     surprisingly
    0.62
     unexpectedly
    0.61
     svůj
    0.60
     scathing
    0.59
     tumultuous
    0.59
     impressive
    0.58
     свою
    0.57
     spectacularly
    0.57
     unprecedented
    0.55
    Act Density 0.010%

    No Known Activations