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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    argument
    -0.07
    580
    -0.07
     fic
    -0.06
     {}).
    -0.06
    annot
    -0.06
     argument
    -0.06
    оть
    -0.06
    /GPL
    -0.06
     putStrLn
    -0.06
    	location
    -0.06
    POSITIVE LOGITS
     запас
    0.07
     гриб
    0.07
     Moder
    0.07
     drip
    0.07
    paredStatement
    0.06
     honour
    0.06
    ountain
    0.06
     stepping
    0.06
    _eng
    0.06
     Patriot
    0.06
    Act Density 0.054%

    No Known Activations