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

    Neuronpedia

    INDEX
    Explanations

    Eighth and ninth grade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skapa
    -0.08
     degener
    -0.08
    atak
    -0.08
     system
    -0.08
     ranging
    -0.07
     staggering
    -0.07
     δημιουργ
    -0.07
     assigning
    -0.07
     ness
    -0.07
     whisper
    -0.07
    POSITIVE LOGITS
    ousal
    0.09
     persp
    0.08
     corrente
    0.08
    Cab
    0.08
     Pause
    0.08
    etso
    0.08
     bouquets
    0.08
     Dubrov
    0.08
    Dung
    0.08
     divorce
    0.08
    Act Density 0.005%

    No Known Activations