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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     etter
    -0.06
     exploration
    -0.06
     Sort
    -0.06
    Democratic
    -0.06
    	move
    -0.06
    olving
    -0.06
    騎
    -0.06
     Winn
    -0.06
     сторону
    -0.06
    улю
    -0.06
    POSITIVE LOGITS
     широк
    0.08
     США
    0.08
    mods
    0.07
    sic
    0.07
     Electronics
    0.07
    fik
    0.07
    ิช
    0.06
    ρι
    0.06
     Cunningham
    0.06
    amphetamine
    0.06
    Act Density 0.008%

    No Known Activations