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

    Neuronpedia

    INDEX
    Explanations

    python print statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    йы
    0.82
    ির
    0.78
    с
    0.78
    િંગ
    0.75
    čnost
    0.71
    ະຍ
    0.71
    ни
    0.70
    йи
    0.68
    دة
    0.68
    дного
    0.67
    POSITIVE LOGITS
     i
    0.75
    0.74
     and
    0.73
     ﺍ
    0.71
     ο
    0.71
     и
    0.71
    RR
    0.69
     কেননা
    0.68
     $:
    0.68
     were
    0.68
    Act Density 0.000%

    No Known Activations