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

    Neuronpedia

    INDEX
    Explanations

    lists and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     luggage
    0.48
     పిల్ల
    0.45
     प्रमुख
    0.42
    子女
    0.42
     děti
    0.39
    durationType
    0.39
     అంశ
    0.38
     firewood
    0.38
    apadani
    0.38
    ﻩ
    0.38
    POSITIVE LOGITS
     veut
    0.44
     Tabor
    0.42
    wier
    0.40
    weiter
    0.40
     vermelho
    0.40
    win
    0.39
    hnt
    0.39
    ubi
    0.39
     Wettbewer
    0.39
    phi
    0.38
    Act Density 0.726%

    No Known Activations