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

    Neuronpedia

    INDEX
    Explanations

    options and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faucets
    0.42
    letter
    0.42
     tobacco
    0.41
    オ
    0.41
     buckets
    0.41
    াকর
    0.40
    აღ
    0.40
     BECAUSE
    0.39
    ματα
    0.39
     Regulations
    0.39
    POSITIVE LOGITS
    បង្ហាញ
    0.52
     presencia
    0.50
    azaar
    0.46
     душа
    0.45
    ENSIONS
    0.44
    اليا
    0.44
    Ongoing
    0.44
    ade
    0.43
    Ú
    0.43
     visione
    0.43
    Act Density 0.000%

    No Known Activations