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

    Neuronpedia

    INDEX
    Explanations

    relative refined restart unique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ઘરે
    0.39
     అంత
    0.38
    ాలకు
    0.38
     अना
    0.37
     آغاز
    0.37
     کلی
    0.35
     빨
    0.35
    ליו
    0.34
    ನು
    0.34
     சிக்க
    0.34
    POSITIVE LOGITS
     Inclusion
    0.49
     improving
    0.46
     inclusion
    0.44
    INCLUDE
    0.44
    mnist
    0.41
     coaching
    0.41
     inclus
    0.40
    imbing
    0.39
     tele
    0.39
    enf
    0.39
    Act Density 0.000%

    No Known Activations