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

    Neuronpedia

    INDEX
    Explanations

    events unfolding soon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     είναι
    0.99
     является
    0.95
     tienes
    0.91
     ඔබේ
    0.91
     esteja
    0.89
     yra
    0.86
     adalah
    0.86
     हैं
    0.85
    erequisite
    0.85
    дится
    0.85
    POSITIVE LOGITS
     Shortly
    2.03
     Soon
    1.97
     Suddenly
    1.86
     soon
    1.86
     Subsequently
    1.83
     Eventually
    1.81
     вскоре
    1.80
    Shortly
    1.79
    Soon
    1.76
    Subsequently
    1.76
    Act Density 0.187%

    No Known Activations