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

    Neuronpedia

    INDEX
    Explanations

    imaginative populated worlds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mundial
    0.72
     world
    0.67
    world
    0.64
     wereld
    0.64
    世界
    0.59
     worldwide
    0.59
     миро
    0.59
     maail
    0.59
     weltweit
    0.59
     বিশ্বে
    0.59
    POSITIVE LOGITS
     inhabited
    0.79
     populated
    0.76
     populate
    0.64
     насе
    0.59
    populate
    0.57
    populated
    0.56
     parallel
    0.53
     occupied
    0.53
     inhabitants
    0.53
     ruled
    0.52
    Act Density 0.019%

    No Known Activations