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

    Neuronpedia

    INDEX
    Explanations

    contributing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すべての
    0.63
     approx
    0.59
     all
    0.59
     approximately
    0.59
     todas
    0.57
     each
    0.55
     during
    0.52
     semua
    0.52
     وعلى
    0.52
     كافة
    0.52
    POSITIVE LOGITS
    别人的
    0.76
    নিজের
    0.75
     Someone
    0.70
     someone
    0.66
    他人
    0.66
    别人
    0.64
     iemand
    0.63
    Someone
    0.63
    একটা
    0.63
     quelqu
    0.62
    Act Density 0.000%

    No Known Activations