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

    Neuronpedia

    INDEX
    Explanations

    points gained/lost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ({
    0.51
    ({"
    0.47
     ({
    0.46
    ({'
    0.44
    ্মা
    0.44
    provide
    0.43
     [{"
    0.42
    ([{
    0.40
    {(-
    0.40
    ([])
    0.39
    POSITIVE LOGITS
    দেশিক
    0.41
     selectivity
    0.40
    Всем
    0.40
     Trat
    0.38
     onus
    0.38
     Faz
    0.38
     విలువ
    0.38
    tou
    0.37
    تس
    0.37
    Faz
    0.37
    Act Density 0.000%

    No Known Activations