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

    Neuronpedia

    INDEX
    Explanations

    may, might, you, your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ément
    0.62
    HAO
    0.60
    Coming
    0.60
    正在
    0.60
    त्वा
    0.60
     donning
    0.59
    लोर
    0.59
    实现了
    0.59
     निभाने
    0.59
    Upcoming
    0.59
    POSITIVE LOGITS
     may
    1.32
     might
    1.19
     you
    1.17
     bạn
    1.07
    you
    1.05
    may
    1.04
    อาจ
    1.04
     your
    1.02
    您可以
    1.01
    您
    1.01
    Act Density 0.000%

    No Known Activations