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

    Neuronpedia

    INDEX
    Explanations

    over a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ով
    0.37
    发挥
    0.36
    وْ
    0.36
    ﻮ
    0.35
    кто
    0.35
    ગે
    0.34
    呑
    0.33
     onward
    0.33
     रिलेटेड
    0.32
    రకు
    0.32
    POSITIVE LOGITS
     over
    2.14
     протягом
    1.90
    Over
    1.52
     över
    1.38
     über
    1.34
     Over
    1.34
     selama
    1.30
    over
    1.24
     throughout
    1.23
     tijekom
    1.23
    Act Density 0.026%

    No Known Activations