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

    Neuronpedia

    INDEX
    Explanations

    academic and technical discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    唁
    0.46
    lv
    0.42
    nce
    0.41
     bares
    0.41
    देश
    0.40
    摑
    0.40
    नेशन
    0.39
     politik
    0.39
     Londres
    0.38
    andr
    0.38
    POSITIVE LOGITS
     \
    0.52
    0.50
     تقریبا
    0.45
     (\
    0.45
    +\
    0.43
     (!)
    0.43
    Cleanup
    0.42
     nghiên
    0.42
     überw
    0.42
     x
    0.42
    Act Density 0.012%

    No Known Activations