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

    Neuronpedia

    INDEX
    Explanations

    xml

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gareth
    -0.08
    �
    -0.08
     meilleur
    -0.08
    isten
    -0.08
     descent
    -0.07
    phony
    -0.07
    .boot
    -0.07
     Biden
    -0.07
     benefited
    -0.07
     jente
    -0.07
    POSITIVE LOGITS
     XML
    0.13
     xml
    0.11
    /XML
    0.09
    Xml
    0.09
    	xml
    0.08
     Xml
    0.08
    XML
    0.08
    xml
    0.08
    ､
    0.08
     İzmir
    0.07
    Act Density 0.011%

    No Known Activations