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

    Neuronpedia

    INDEX
    Explanations

    city and its equivalents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒄩
    0.37
     nascetur
    0.36
    承包人
    0.36
    kernel
    0.35
    adura
    0.35
     Kernel
    0.35
    㑒
    0.35
    ārt
    0.34
    ˦
    0.34
    包人
    0.34
    POSITIVE LOGITS
     city
    4.63
    city
    4.09
    City
    3.80
     City
    3.75
     शहर
    3.64
     città
    3.61
     cidade
    3.55
     ciudad
    3.47
     CITY
    3.47
     cities
    3.39
    Act Density 0.120%

    No Known Activations