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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acceptance
    -0.07
    	engine
    -0.06
    ф
    -0.06
     declare
    -0.06
    NUMBER
    -0.06
     жизнь
    -0.06
     importantes
    -0.06
    Builder
    -0.06
    (detail
    -0.06
    plorer
    -0.06
    POSITIVE LOGITS
    function
    0.08
     function
    0.07
    DOI
    0.07
     Matlab
    0.07
    	function
    0.07
     назнач
    0.07
     diminishing
    0.07
    Model
    0.07
     Axel
    0.07
     functions
    0.07
    Act Density 0.002%

    No Known Activations