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

    Neuronpedia

    INDEX
    Explanations

    craftsmanship and magical tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cdt
    0.41
    Wend
    0.39
    ાર્થી
    0.37
     wala
    0.37
     ejer
    0.37
     petitioned
    0.36
     પતિ
    0.36
     tuz
    0.36
     voy
    0.35
    罘
    0.35
    POSITIVE LOGITS
     handy
    0.79
     trusty
    0.69
     dedicated
    0.60
     conveniently
    0.59
     nifty
    0.57
     convenient
    0.57
     calculator
    0.55
     versatile
    0.55
     robust
    0.52
     precise
    0.52
    Act Density 0.000%

    No Known Activations