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

    Neuronpedia

    INDEX
    Explanations

    American overviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nee
    0.43
    licht
    0.41
     haies
    0.40
    넹
    0.40
    eterm
    0.39
    ába
    0.39
     ඇත
    0.38
    ịp
    0.38
    implemented
    0.38
    ahang
    0.38
    POSITIVE LOGITS
     American
    0.57
     Encyclopedia
    0.52
     Skyscrapers
    0.47
     Americans
    0.47
     美国
    0.46
     американ
    0.45
     skyscrapers
    0.45
     George
    0.44
     আমেরিকান
    0.44
     G
    0.43
    Act Density 0.001%

    No Known Activations