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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     jovens
    0.82
    បែប
    0.80
     деца
    0.76
    Описание
    0.73
    Как
    0.71
    Если
    0.71
    Без
    0.71
    安心
    0.71
    肐
    0.71
    ోంది
    0.70
    POSITIVE LOGITS
     l
    0.79
     st
    0.70
     tra
    0.70
    ↵
    0.67
     me
    0.67
     sunset
    0.67
     trillions
    0.67
     iş
    0.65
    onders
    0.64
    omere
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.