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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еними
    -0.07
     exercitation
    -0.06
    нач
    -0.06
     <|
    -0.06
     versatility
    -0.06
    SORT
    -0.06
    LAT
    -0.06
     sway
    -0.06
     destiny
    -0.06
    ื
    -0.06
    POSITIVE LOGITS
    	window
    0.07
    лоб
    0.07
    είο
    0.06
     porter
    0.06
     menos
    0.06
     intval
    0.06
     سیستم
    0.06
     انتخابات
    0.06
     monde
    0.06
    (urls
    0.06
    Act Density 0.006%

    No Known Activations