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

    Neuronpedia

    INDEX
    Explanations

    information, numbers, and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sha
    0.43
     SHA
    0.40
    ba
    0.40
    cha
    0.39
     ഉണ്ട്
    0.38
     problemen
    0.37
    ichar
    0.37
    Czechoslovakia
    0.36
     serii
    0.36
    heast
    0.36
    POSITIVE LOGITS
    ₮
    0.43
    틸
    0.43
    ]]:
    0.41
    ंद्र
    0.39
     दि
    0.38
     adjustable
    0.38
     photoshoot
    0.38
    >:
    0.38
     디지털
    0.38
     carelessly
    0.38
    Act Density 0.000%

    No Known Activations