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

    Neuronpedia

    INDEX
    Explanations

    place names ending in burg, bourne, or similar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assapi
    0.69
    ленных
    0.64
    lyPlugin
    0.62
     meriye
    0.60
     কলকাত
    0.59
     ľud
    0.59
    akkhanam
    0.58
     вершин
    0.58
     людьми
    0.58
     llrp
    0.57
    POSITIVE LOGITS
     way
    0.70
    Thy
    0.67
    '
    0.61
    Cogn
    0.61
    I
    0.59
    B
    0.58
    Steam
    0.58
    Aer
    0.57
    =
    0.57
    Ar
    0.57
    Act Density 0.042%

    No Known Activations