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

    Neuronpedia

    INDEX
    Explanations

    Łužickoserbski

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𐰤
    0.39
     Siena
    0.39
    న్నారు
    0.38
     Owners
    0.38
     Assim
    0.38
     محک
    0.38
    RUPTION
    0.38
     Overseas
    0.37
     Sioux
    0.37
    闽
    0.37
    POSITIVE LOGITS
     dź
    0.65
     dokład
    0.57
    ź
    0.56
     bł
    0.53
     staw
    0.52
     knih
    0.52
     powst
    0.50
     naw
    0.50
     hodnot
    0.50
     snad
    0.49
    Act Density 0.000%

    No Known Activations