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

    Neuronpedia

    INDEX
    Explanations

    Hebrew and Arabic sentence continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಏನು
    0.92
    denly
    0.91
     bureaucrats
    0.91
     ಅವರನ್ನು
    0.89
     maior
    0.89
     ವಿಧಾನಸಭಾ
    0.88
     sexuales
    0.88
     lepro
    0.87
     postice
    0.86
     रिक्वायरमेंट
    0.86
    POSITIVE LOGITS
     ת
    0.95
    إ
    0.93
    الم
    0.87
    م
    0.86
     مض
    0.80
    ال
    0.80
    إن
    0.79
    ف
    0.79
    מ
    0.79
    الت
    0.79
    Act Density 0.010%

    No Known Activations