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

    Neuronpedia

    INDEX
    Explanations

    city

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hor
    0.92
    lor
    0.85
    hal
    0.83
     Howard
    0.78
     Euch
    0.77
    har
    0.75
     Spect
    0.75
    hens
    0.74
    iar
    0.74
    Harrison
    0.73
    POSITIVE LOGITS
     City
    1.91
     CITY
    1.90
     city
    1.89
    City
    1.83
    city
    1.74
    CITY
    1.69
    Cities
    1.56
     cities
    1.55
     Cities
    1.52
     città
    1.42
    Act Density 0.991%

    No Known Activations