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

    Neuronpedia

    INDEX
    Explanations

    settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Activity
    -0.07
     будуть
    -0.07
    なかった
    -0.07
    )viewDidLoad
    -0.06
     جي
    -0.06
     reform
    -0.06
    Breadcrumb
    -0.06
     Infantry
    -0.06
    activated
    -0.06
    	mkdir
    -0.06
    POSITIVE LOGITS
     caps
    0.07
     jewish
    0.07
    -cookie
    0.07
     preferences
    0.06
     dispon
    0.06
     unbelie
    0.06
     gre
    0.06
    	selected
    0.06
    Settings
    0.06
     shrinking
    0.06
    Act Density 0.010%

    No Known Activations