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

    Neuronpedia

    INDEX
    Explanations

    well, smoothly, poorly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    屉
    0.67
    ᑎ
    0.64
    reachable
    0.61
    денциа
    0.61
    攢
    0.60
     подвер
    0.60
    ຕິດຕໍ່
    0.58
    䒑
    0.58
    NotIn
    0.58
    ậm
    0.58
    POSITIVE LOGITS
     well
    4.16
    well
    3.34
     Well
    3.17
    Well
    3.15
     excellently
    3.09
     хорошо
    3.04
     nicely
    3.01
     dobrze
    2.95
     WELL
    2.95
     잘
    2.93
    Act Density 1.020%

    No Known Activations