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

    Neuronpedia

    INDEX
    Explanations

    cities and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    煐
    0.36
    颛
    0.34
    驷
    0.32
    ของการ
    0.31
     변화
    0.30
     반복
    0.30
     효과
    0.30
    ᕇ
    0.29
    强调
    0.29
     అధికారు
    0.29
    POSITIVE LOGITS
     cities
    0.56
     cidades
    0.56
     مدينة
    0.56
     cidade
    0.53
     London
    0.52
     città
    0.49
    مدينة
    0.49
     ciudades
    0.49
     ciudad
    0.48
     miasta
    0.47
    Act Density 0.070%

    No Known Activations