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

    Neuronpedia

    INDEX
    Explanations

    providing explanations again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     而且
    0.38
     ଦ
    0.37
     ପ୍ର
    0.36
    ^{\
    0.36
    而且
    0.35
     ‌
    0.35
     ln
    0.35
    AppCompat
    0.35
     adheres
    0.34
     Hertfordshire
    0.34
    POSITIVE LOGITS
     опять
    0.52
    นี้
    0.51
    要知道
    0.46
    냐면
    0.44
     bunu
    0.44
     nuovamente
    0.44
    again
    0.43
    это
    0.43
    这个人
    0.43
    ри
    0.43
    Act Density 0.131%

    No Known Activations