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

    Neuronpedia

    INDEX
    Explanations

    quantities and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Finite
    0.50
     dàng
    0.48
     Noetherian
    0.48
    larında
    0.47
     सौंद
    0.47
    ganggu
    0.47
    on
    0.47
     τρόπο
    0.47
    finite
    0.46
     Rhine
    0.46
    POSITIVE LOGITS
    페
    0.48
    你
    0.46
    您
    0.45
     Вам
    0.44
    ليك
    0.44
     derivations
    0.43
     antiguas
    0.43
    ález
    0.42
    ė
    0.41
    дир
    0.40
    Act Density 0.000%

    No Known Activations