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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affirmative
    -0.06
    ulti
    -0.06
     مون
    -0.06
     skate
    -0.06
     glance
    -0.06
    站
    -0.06
    .ro
    -0.06
     mg
    -0.06
     putt
    -0.06
    gmail
    -0.06
    POSITIVE LOGITS
    JSGlobalScope
    0.06
     physiological
    0.06
     fieldName
    0.06
    tweets
    0.06
     Geneva
    0.06
     [...]↵↵
    0.06
          ↵      ↵
    0.06
     مختلف
    0.06
    에는
    0.06
     harvesting
    0.06
    Act Density 0.001%

    No Known Activations