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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тоді
    -0.07
     على
    -0.07
     bathtub
    -0.07
    ense
    -0.07
    _daily
    -0.07
     Circle
    -0.07
    Χ
    -0.07
     TEntity
    -0.07
     düğ
    -0.06
     Depart
    -0.06
    POSITIVE LOGITS
     совет
    0.06
    ustrial
    0.06
    ={!
    0.06
          ↵
    0.06
    tributes
    0.06
    нак
    0.06
     BLACK
    0.06
     알아
    0.06
    423
    0.06
    ’,
    0.06
    Act Density 0.132%

    No Known Activations