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

    Neuronpedia

    INDEX
    Explanations

    possibility and potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Необходимо
    0.45
    គឺ
    0.44
     stets
    0.43
     perfecting
    0.43
     především
    0.41
     dominates
    0.41
     необхідно
    0.40
     emphasized
    0.40
     przede
    0.40
     подробно
    0.40
    POSITIVE LOGITS
    有可能
    0.92
     occasionally
    0.91
     niektórych
    0.89
     conceivably
    0.89
     SOME
    0.88
     некоторых
    0.86
    偶尔
    0.84
     moguće
    0.83
     COULD
    0.83
     attempt
    0.82
    Act Density 0.360%

    No Known Activations