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

    Neuronpedia

    INDEX
    Explanations

    quantities worldwide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     клиен
    0.57
    分手
    0.54
    辊
    0.53
     सरिया
    0.52
     ज्वाइन
    0.50
    🎈
    0.50
    搅拌
    0.48
    进口
    0.48
     Cherry
    0.48
    购
    0.48
    POSITIVE LOGITS
     billions
    0.97
     trillions
    0.92
     worldwide
    0.88
     world
    0.86
     humanity
    0.84
     terrestrial
    0.83
     trillion
    0.82
     extin
    0.80
     миллиар
    0.80
     species
    0.79
    Act Density 0.102%

    No Known Activations