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

    Neuronpedia

    INDEX
    Explanations

    us/en URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दुनियाभर
    0.46
     العالمية
    0.44
     мировой
    0.43
     миро
    0.43
     weltweit
    0.43
    worldwide
    0.43
     worldwide
    0.42
     نړ
    0.42
     ഇന്ത്യൻ
    0.42
     mundial
    0.41
    POSITIVE LOGITS
    en
    0.44
     Region
    0.42
     province
    0.41
     Multiple
    0.40
    Region
    0.40
     Provinz
    0.39
     Que
    0.39
    Cent
    0.39
     Dublin
    0.38
     Took
    0.38
    Act Density 0.006%

    No Known Activations