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

    Neuronpedia

    INDEX
    Explanations

    following descriptions with actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    當然
    0.49
     ขาย
    0.43
    卖
    0.43
     obviamente
    0.43
     oczywiście
    0.42
    sell
    0.42
    当然
    0.41
    ību
    0.41
     Dirt
    0.40
     красиво
    0.40
    POSITIVE LOGITS
    requires
    0.48
     requires
    0.46
    constrained
    0.46
    する必要があります
    0.42
     requiring
    0.42
     requiere
    0.41
     occupying
    0.41
    require
    0.40
     occupies
    0.40
     utilising
    0.40
    Act Density 0.004%

    No Known Activations