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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Articles
    -0.06
     kids
    -0.06
     outlining
    -0.06
    fuck
    -0.06
     PST
    -0.06
     Approx
    -0.06
     Redskins
    -0.06
     Engine
    -0.06
    úmeros
    -0.06
     Internal
    -0.06
    POSITIVE LOGITS
     ≠
    0.07
     gri
    0.06
    الف
    0.06
    comput
    0.06
    folio
    0.06
     Miracle
    0.06
     Olympus
    0.06
    			
↵			
↵
    0.06
    	 
↵
    0.06
    [f
    0.06
    Act Density 0.003%

    No Known Activations