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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     siêu
    0.52
    আপনি
    0.49
     mutter
    0.47
     super
    0.46
     çap
    0.45
     reap
    0.44
    k
    0.44
     cruelty
    0.44
    超
    0.44
    রাই
    0.44
    POSITIVE LOGITS
    люс
    0.50
     instructive
    0.47
    دق
    0.45
     Hohen
    0.43
     Вол
    0.43
     ដោយ
    0.42
    ыргыз
    0.41
     식으로
    0.41
     Condiciones
    0.41
    :\
    0.41
    Act Density 0.000%

    No Known Activations