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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overall
    1.75
     Overall
    1.68
    overall
    1.61
    Overall
    1.58
    整體
    1.48
    整体
    1.31
    总体
    1.31
     excellent
    1.23
     Excellent
    1.21
     AMAZING
    1.19
    POSITIVE LOGITS
     напомина
    0.66
    няются
    0.65
    лур
    0.63
    ymmetries
    0.60
    ประชาชน
    0.60
    ozyg
    0.59
     acontecimientos
    0.59
     жителей
    0.59
     жители
    0.58
     пригла
    0.57
    Act Density 0.039%

    No Known Activations