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

    Neuronpedia

    INDEX
    Explanations

    dumplings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ной
    0.92
    בּ
    0.89
     hues
    0.89
    0.89
    爰
    0.88
     cáo
    0.85
    ג
    0.84
     grassland
    0.82
     коды
    0.82
     которых
    0.81
    POSITIVE LOGITS
    ifferentiating
    1.00
     ويمكن
    0.96
     Handmade
    0.91
     traject
    0.89
    japanese
    0.89
    পিং
    0.89
    cussions
    0.87
    arci
    0.87
    檬
    0.87
     convexo
    0.86
    Act Density 0.002%

    No Known Activations