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

    Neuronpedia

    INDEX
    Explanations

    say "("

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agen
    0.39
     페
    0.38
    imum
    0.37
    펜
    0.36
     tris
    0.34
     Calder
    0.33
    സു
    0.33
    좋
    0.33
     मौ
    0.32
     тобі
    0.32
    POSITIVE LOGITS
     setSnackbar
    0.34
    "=>
    0.34
    PLL
    0.33
    лакти
    0.32
    ukaemia
    0.32
    ")+
    0.31
     திரைப்படம்
    0.31
    "-
    0.31
    '&
    0.31
     BBS
    0.31
    Act Density 0.008%

    No Known Activations