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

    Neuronpedia

    INDEX
    Explanations

    every possibility, detail, or event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    0.97
     plupart
    0.95
    Wallpaper
    0.89
    ast
    0.84
    Α
    0.83
    Rejected
    0.83
    ש
    0.83
    Quite
    0.82
    ف
    0.82
    k
    0.82
    POSITIVE LOGITS
     nuance
    1.20
     conceivable
    1.18
     nook
    1.08
     nuances
    1.06
     imaginable
    1.05
     damn
    1.00
     możli
    0.98
     darn
    0.93
     single
    0.90
     bit
    0.90
    Act Density 0.009%

    No Known Activations