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

    Neuronpedia

    INDEX
    Explanations

    beyond higher than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಯಾವುದೇ
    0.55
    কোনও
    0.51
     bukan
    0.50
     değil
    0.50
     แต่
    0.49
     लेकिन
    0.47
     모든
    0.47
     nejen
    0.47
    any
    0.46
    tidak
    0.46
    POSITIVE LOGITS
     this
    0.46
     svojoj
    0.44
     này
    0.42
     هذا
    0.42
     senc
    0.41
    essentially
    0.41
     a
    0.41
    นี้
    0.41
     fundamentally
    0.40
     essentially
    0.40
    Act Density 0.037%

    No Known Activations