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

    Neuronpedia

    INDEX
    Explanations

    us cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ણમાં
    0.72
     Mahoney
    0.69
     macromolecules
    0.68
    adder
    0.68
    ース
    0.66
    灸
    0.66
     Supers
    0.66
     reintegr
    0.66
     አመ
    0.65
     overlying
    0.65
    POSITIVE LOGITS
     Chicago
    1.48
     Houston
    1.48
    Chicago
    1.47
     Los
    1.42
     Atlanta
    1.42
    Los
    1.41
     Boston
    1.40
    Atlanta
    1.39
    Houston
    1.36
    Boston
    1.35
    Act Density 0.024%

    No Known Activations