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

    Neuronpedia

    INDEX
    Explanations

    flexible and flexibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഉറ
    0.53
    突出
    0.51
    され
    0.50
    ería
    0.49
     от
    0.47
    akers
    0.47
    确保
    0.47
    }]}\
    0.47
    lation
    0.46
    aken
    0.46
    POSITIVE LOGITS
     flexible
    1.80
     flexibility
    1.63
     Flexible
    1.61
     flexibilidad
    1.56
    Flexible
    1.55
     Flexibility
    1.52
     fleks
    1.52
    Flex
    1.41
     flexibly
    1.38
     flexibles
    1.38
    Act Density 0.071%

    No Known Activations