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

    Neuronpedia

    INDEX
    Explanations

    language and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     و
    0.52
     وَ
    0.49
     and
    0.48
     আৰু
    0.46
     ۽
    0.45
     تے
    0.44
     &
    0.42
    খানি
    0.41
     bụ
    0.40
     circulaire
    0.40
    POSITIVE LOGITS
     pessoas
    0.53
    pessoas
    0.51
     insanlar
    0.50
    people
    0.48
     люди
    0.48
     people
    0.47
     ಜನರು
    0.47
    निटी
    0.46
     ओवरटाइम
    0.46
    soldiers
    0.45
    Act Density 0.001%

    No Known Activations