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

    Neuronpedia

    INDEX
    Explanations

    url segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wan
    0.56
     طلبه
    0.54
     Lebanon
    0.53
    疑问
    0.52
     Chile
    0.52
     Urdu
    0.52
     taxing
    0.51
     Hokkaido
    0.50
    Shopping
    0.50
     Där
    0.50
    POSITIVE LOGITS
    тен
    0.80
     ತಿಳಿದ
    0.66
     முதல்
    0.64
    一批
    0.61
     diccionario
    0.61
    ވެ
    0.60
    ಕ್ಕಿಂತ
    0.60
     இந்த
    0.59
     दिस
    0.59
    முதல்
    0.58
    Act Density 0.020%

    No Known Activations