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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Escape
    -0.07
     Marx
    -0.07
     interests
    -0.07
     chiefs
    -0.07
    projects
    -0.07
    pictures
    -0.07
     guns
    -0.07
     estimator
    -0.06
     escaping
    -0.06
     Plates
    -0.06
    POSITIVE LOGITS
     مث
    0.06
    	Set
    0.06
     نمایش
    0.06
     Aless
    0.06
     sez
    0.06
    �
    0.06
    	Dictionary
    0.06
    _registered
    0.06
     "\<
    0.06
    @(
    0.06
    Act Density 0.011%

    No Known Activations