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

    Neuronpedia

    INDEX
    Explanations

    and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extraordinaire
    0.47
    ❯
    0.44
     ब्रा
    0.43
     receivables
    0.43
     محد
    0.43
     부
    0.42
     Income
    0.41
     उत्तरा
    0.41
     Excess
    0.41
    شرات
    0.41
    POSITIVE LOGITS
    và
    0.47
     и
    0.47
     and
    0.45
     ۽
    0.44
     અને
    0.43
    ný
    0.42
     và
    0.42
     dhe
    0.41
     andRow
    0.41
    chrono
    0.41
    Act Density 0.001%

    No Known Activations