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

    Neuronpedia

    INDEX
    Explanations

    importance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dụng
    0.46
     व्याज
    0.45
     espírito
    0.45
     tecnologías
    0.44
    是
    0.44
    <ul>
    0.44
     сили
    0.43
     فکر
    0.43
    主な
    0.43
     দুর্বল
    0.43
    POSITIVE LOGITS
    Importance
    0.71
     importance
    0.68
     Importance
    0.65
     इंपॉर्ट
    0.61
    த்துவம்
    0.60
    importance
    0.58
    ar
    0.57
    Important
    0.54
    t
    0.53
    的重要性
    0.53
    Act Density 0.014%

    No Known Activations