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

    Neuronpedia

    INDEX
    Explanations

    code licensing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blue
    -0.07
    Paul
    -0.07
     suitability
    -0.06
     Auss
    -0.06
     blue
    -0.06
     YELLOW
    -0.06
     ger
    -0.06
    Jam
    -0.06
    สด
    -0.06
    hab
    -0.06
    POSITIVE LOGITS
               ↵
    0.07
                                  ↵
    0.07
          ↵
    0.07
       ↵
    0.07
         ↵
    0.07
    ings
    0.07
    _crop
    0.07
                                   ↵
    0.07
        	↵
    0.06
    meeting
    0.06
    Act Density 0.004%

    No Known Activations