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

    Neuronpedia

    INDEX
    Explanations

    recursive algorithms with indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्फोट
    0.69
     stuck
    0.65
     හ
    0.64
    ปฏิบัติ
    0.64
     sự
    0.63
     উপকার
    0.63
     proceeded
    0.63
     फायदे
    0.63
    අ
    0.62
    Princ
    0.62
    POSITIVE LOGITS
     марки
    0.74
    +},
    0.73
     रिव्यू
    0.72
     ভিত্তি
    0.68
    ដែ
    0.67
    гом
    0.66
    områ
    0.66
     бя
    0.65
    +|
    0.65
    graded
    0.65
    Act Density 0.026%

    No Known Activations