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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Record
    -0.07
    .tr
    -0.06
     Coke
    -0.06
    “For
    -0.06
     taller
    -0.06
     Nose
    -0.06
     serene
    -0.06
    .attrs
    -0.06
     auss
    -0.06
     siding
    -0.05
    POSITIVE LOGITS
    logfile
    0.07
    战
    0.07
     RS
    0.07
    结束
    0.07
     싸
    0.06
     ссыл
    0.06
     применя
    0.06
     Occupy
    0.06
      
↵
    0.06
    戰
    0.06
    Act Density 0.001%

    No Known Activations