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

    Neuronpedia

    INDEX
    Explanations

    governments and societies

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    店内
    0.47
    erven
    0.46
    bleeds
    0.44
     Tricks
    0.44
     fetches
    0.44
     tugas
    0.43
     œufs
    0.42
     tricks
    0.42
    Tasks
    0.41
    🧁
    0.41
    POSITIVE LOGITS
     governments
    2.66
     nations
    2.52
     societies
    2.45
     civilizations
    2.34
     Governments
    2.25
     cultures
    2.02
     countries
    2.00
     gobiernos
    1.92
     Societies
    1.88
    govern
    1.86
    Act Density 0.409%

    No Known Activations