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

    Neuronpedia

    INDEX
    Explanations

    infinity stone fragment, emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    阵
    0.47
     Lucille
    0.45
    ס
    0.43
    Circles
    0.43
    Vector
    0.43
    迪士
    0.42
    اع
    0.42
    Bengal
    0.42
     dispatcher
    0.41
    Jefferson
    0.41
    POSITIVE LOGITS
     laughed
    0.50
    ır
    0.48
     پاک
    0.44
    <unused77>
    0.43
     обра
    0.43
     पा
    0.42
    鬼
    0.42
    ક્ર
    0.42
    ő
    0.41
     aasta
    0.41
    Act Density 0.002%

    No Known Activations