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

    Neuronpedia

    INDEX
    Explanations

    somewhat grumpy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     könnt
    0.54
     Conseil
    0.46
     అమె
    0.46
     الأمريكي
    0.44
    حيان
    0.43
     öffentlich
    0.43
    ៉
    0.43
    cession
    0.42
     ఆర్థిక
    0.42
     美国
    0.42
    POSITIVE LOGITS
    ف
    0.51
     dashboards
    0.50
    và
    0.46
    ξε
    0.45
    DEFINE
    0.45
    これから
    0.45
    טן
    0.43
    けた
    0.43
     arteries
    0.42
    データ
    0.41
    Act Density 0.056%

    No Known Activations