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

    Neuronpedia

    INDEX
    Explanations

    comparisons of size or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خوب
    0.66
     schönen
    0.65
     خوبی
    0.63
     maravilh
    0.62
     કોઈ
    0.62
    気に入
    0.57
     niets
    0.57
    ateful
    0.56
     schöne
    0.56
     maravilloso
    0.56
    POSITIVE LOGITS
     faster
    1.74
     fewer
    1.71
     stronger
    1.67
     quicker
    1.66
     greater
    1.66
     denser
    1.64
    보다
    1.63
     higher
    1.63
    更高的
    1.63
     richer
    1.62
    Act Density 1.219%

    No Known Activations