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

    Neuronpedia

    INDEX
    Explanations

    covering everything / includes all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কিংবা
    0.52
     அல்லது
    0.46
     किंवा
    0.44
     혹은
    0.43
    あるいは
    0.42
     অথবা
    0.42
    または
    0.42
     katika
    0.40
     yoki
    0.40
     veya
    0.39
    POSITIVE LOGITS
     semua
    0.75
     всех
    0.73
     wszystkich
    0.70
     सभी
    0.69
     både
    0.68
     all
    0.67
     всіх
    0.66
     cả
    0.65
     všech
    0.65
     both
    0.64
    Act Density 0.283%

    No Known Activations