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

    Neuronpedia

    INDEX
    Explanations

    by far

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     одним
    0.42
     někter
    0.42
     অন্যতম
    0.41
    的重要
    0.41
     egyik
    0.41
     یکی
    0.41
     одном
    0.41
     niektórych
    0.40
     jednego
    0.39
     برخی
    0.39
    POSITIVE LOGITS
     by
    1.63
     By
    1.43
    By
    1.38
    by
    1.25
     oleh
    1.17
     BY
    1.16
     far
    1.02
     бы
    1.02
     bằng
    0.97
     توسط
    0.97
    Act Density 0.028%

    No Known Activations