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

    Neuronpedia

    INDEX
    Explanations

    groups of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dépenses
    0.32
     ተመሳሳይ
    0.31
     ਇੱਕ
    0.31
     미국의
    0.31
    RatingDiff
    0.29
    หนึ่ง
    0.29
    面白い
    0.29
    приклад
    0.29
     어떤
    0.29
    တစ်ခု
    0.29
    POSITIVE LOGITS
     non
    0.39
     residents
    0.39
     stakeholders
    0.39
     adults
    0.38
     populations
    0.38
     migrants
    0.38
     adultos
    0.37
     asymptomatic
    0.37
     students
    0.36
     unvaccinated
    0.36
    Act Density 0.001%

    No Known Activations