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

    Neuronpedia

    INDEX
    Explanations

    Nepal and Nepali terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्पर
    0.58
     لیون
    0.57
    ेंटीना
    0.54
     दिरहम
    0.54
     ব্রাজ
    0.51
     सेलेना
    0.51
    鳗
    0.51
     സ്റ്റ
    0.51
     Myles
    0.50
    庞
    0.49
    POSITIVE LOGITS
     Nepali
    1.66
     Nepal
    1.60
     Kathmandu
    1.54
    Nepal
    1.50
    Nepali
    1.42
     नेपाली
    1.23
     Bhutan
    1.23
     Himalayan
    1.23
     नेपाल
    1.16
     Sikkim
    1.02
    Act Density 0.023%

    No Known Activations