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

    Neuronpedia

    INDEX
    Explanations

    Neti pots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     governs
    -0.10
     impacts
    -0.08
     Columbus
    -0.07
     govern
    -0.07
     denotes
    -0.07
    (flag
    -0.07
     governance
    -0.07
    flags
    -0.07
     flags
    -0.07
    	flag
    -0.07
    POSITIVE LOGITS
     lavage
    0.11
     saline
    0.11
     desperation
    0.10
     Asp
    0.10
     терап
    0.10
     intraven
    0.09
     inhal
    0.09
     intravenous
    0.09
     terape
    0.09
     मरीज
    0.09
    Act Density 0.005%

    No Known Activations