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

    Neuronpedia

    INDEX
    Explanations

    telecommunications broadcasting difficult contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.52
    ການ
    0.51
    Faction
    0.46
    ृति
    0.45
    es
    0.45
    Puerto
    0.44
    Social
    0.44
    een
    0.43
     فروغ
    0.43
    云
    0.43
    POSITIVE LOGITS
     mnoh
    0.53
     vissa
    0.53
     modalCard
    0.52
    staande
    0.51
     потен
    0.50
     DENUMIRE
    0.50
     modellen
    0.50
     namani
    0.49
     plastica
    0.49
     значения
    0.49
    Act Density 0.000%

    No Known Activations