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

    Neuronpedia

    INDEX
    Explanations

    city and country names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Carefully
    0.44
     ette
    0.42
     পাওয়া
    0.40
     Gerade
    0.37
     Amongst
    0.36
     Get
    0.36
     Фонбет
    0.36
    棒
    0.35
     simplify
    0.35
     ब्राह
    0.35
    POSITIVE LOGITS
     city
    0.51
    เมือง
    0.49
     miejscowości
    0.49
     same
    0.49
     cities
    0.48
     towns
    0.48
     cidade
    0.47
     location
    0.46
     locality
    0.45
     town
    0.45
    Act Density 0.001%

    No Known Activations