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

    Neuronpedia

    INDEX
    Explanations

    Ontario, Toronto, cities, provinces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alaska
    0.86
     Alaska
    0.82
    Montana
    0.70
     Montana
    0.66
    北海道
    0.61
    Alberta
    0.61
     Yukon
    0.60
     Spokane
    0.59
     北海道
    0.57
    Vancouver
    0.56
    POSITIVE LOGITS
     Ontario
    0.66
    Ontario
    0.55
     Toronto
    0.54
     Ont
    0.46
     Mississauga
    0.46
    Toronto
    0.45
     ONT
    0.45
     Thackeray
    0.43
     PSW
    0.40
    iele
    0.40
    Act Density 0.017%

    No Known Activations