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

    Neuronpedia

    INDEX
    Explanations

    Sanskrit, Hindi, and spiritual texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    handlungen
    0.66
    ുപത്രി
    0.66
    ⬝
    0.66
    мпания
    0.65
    妏
    0.65
    ಂಗ್
    0.63
    تمبر
    0.63
    पेयी
    0.62
    ಕ್ಸ್
    0.62
    ত্তা
    0.61
    POSITIVE LOGITS
    0.48
     destroy
    0.47
     Yatha
    0.45
        
    0.45
     destroys
    0.44
    abhavena
    0.44
     sukham
    0.43
     suffers
    0.42
     realize
    0.42
     yattha
    0.42
    Act Density 0.005%

    No Known Activations