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

    Neuronpedia

    INDEX
    Explanations

    graduallysooneventually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nếu
    0.60
    если
    0.58
     Если
    0.54
     supposing
    0.53
    Если
    0.52
    如果我们
    0.51
     eğer
    0.50
    上次
    0.49
     якщо
    0.49
     если
    0.48
    POSITIVE LOGITS
     Soon
    1.45
    Soon
    1.41
     soon
    1.40
     Eventually
    1.30
     вскоре
    1.23
    soon
    1.20
    Eventually
    1.19
     eventually
    1.17
     Gradually
    1.15
     Shortly
    1.10
    Act Density 0.060%

    No Known Activations