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

    Neuronpedia

    INDEX
    Explanations

    URLs and websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    絬
    0.39
     unsuitable
    0.38
    低下
    0.37
    ኾ
    0.35
    ጬ
    0.35
    ुष
    0.35
    ঘ্রই
    0.35
     diffère
    0.34
     недостаточно
    0.34
     მხოლოდ
    0.34
    POSITIVE LOGITS
     www
    1.03
    www
    0.98
     website
    0.79
    website
    0.75
     https
    0.71
    https
    0.66
     Website
    0.64
    Website
    0.60
     http
    0.57
     websites
    0.57
    Act Density 0.023%

    No Known Activations