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

    Neuronpedia

    INDEX
    Explanations

    world and society

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Portuguese
    0.40
     micrófono
    0.39
     turkish
    0.39
    Swedish
    0.39
     Hungarian
    0.38
     Moroccan
    0.38
    Turkish
    0.37
     slov
    0.37
     Dutch
    0.37
     portugu
    0.37
    POSITIVE LOGITS
     världen
    1.27
     העולם
    1.25
     세상
    1.22
     दुनिया
    1.19
    世界
    1.17
     society
    1.16
     world
    1.14
     dunia
    1.14
     verden
    1.14
     العالم
    1.13
    Act Density 0.017%

    No Known Activations