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

    Neuronpedia

    INDEX
    Explanations

    conclusions or thank yous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اؤ
    0.49
     módulo
    0.43
    ’).
    0.41
     آپ
    0.40
    ‌്
    0.40
    ಮನ
    0.39
     ­
    0.39
     pār
    0.39
     equivari
    0.39
    …’
    0.38
    POSITIVE LOGITS
    THANK
    0.80
    Conclusion
    0.74
    Bibliography
    0.73
    CONCLUSION
    0.72
     conclusion
    0.71
     Conclusion
    0.70
     THANK
    0.67
    <h3>
    0.66
    <h2>
    0.62
    Thank
    0.62
    Act Density 0.000%

    No Known Activations