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

    Neuronpedia

    INDEX
    Explanations

    some of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     two
    0.70
     three
    0.65
     four
    0.61
     semua
    0.61
     सभी
    0.59
     மூன்று
    0.59
     இரண்டு
    0.58
     tất
    0.57
     drei
    0.55
     두
    0.55
    POSITIVE LOGITS
     najważ
    0.48
     prominent
    0.48
    最有
    0.47
    Other
    0.46
    Olivia
    0.45
     другими
    0.43
     більш
    0.43
     populaire
    0.43
     ഏറ്റവും
    0.43
     wellknown
    0.43
    Act Density 0.051%

    No Known Activations