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

    Neuronpedia

    INDEX
    Explanations

    breakdown of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.32
     એક
    0.29
     An
    0.28
     Sh
    0.28
     Night
    0.27
    ictures
    0.27
     একজন
    0.27
     A
    0.26
     PRO
    0.26
     merupakan
    0.26
    POSITIVE LOGITS
     რომელიც
    0.42
    ของการ
    0.42
     של
    0.41
     waarbij
    0.38
     of
    0.38
    នៃ
    0.37
     của
    0.37
     whereby
    0.36
     ofthe
    0.36
     của
    0.35
    Act Density 0.804%

    No Known Activations