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

    Neuronpedia

    INDEX
    Explanations

    continuation of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.97
     असून
    0.93
     যেমন
    0.85
    കളും
    0.77
    ുകളും
    0.74
    @
    0.73
     gồm
    0.73
    ளான
    0.72
     වන්නේ
    0.72
    有两种
    0.71
    POSITIVE LOGITS
     etc
    5.68
    etc
    5.06
     Etc
    4.60
     usw
    4.49
     ইত্যাদি
    4.45
    等等
    4.39
     आदि
    4.32
     тощо
    4.27
     등이
    4.21
    等
    4.18
    Act Density 0.964%

    No Known Activations