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

    Neuronpedia

    INDEX
    Explanations

    list items followed by etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असून
    0.78
    }|
    0.71
     असलेल्या
    0.70
     |
    0.68
     zarówno
    0.66
    }}(\
    0.66
    ಿಯು
    0.63
     झालेल्या
    0.61
     වන්නේ
    0.60
    이자
    0.60
    POSITIVE LOGITS
     etc
    6.22
    etc
    5.66
     Etc
    5.17
     usw
    4.97
    等
    4.89
    等等
    4.89
     ইত্যাদি
    4.77
    など
    4.72
     आदि
    4.69
     등
    4.65
    Act Density 0.689%

    No Known Activations