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

    Neuronpedia

    INDEX
    Explanations

    why they tend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਬ
    0.43
     Tento
    0.43
    ட்டைகோ
    0.43
    நுட்ப
    0.43
     wunder
    0.43
     Ony
    0.42
    ್ರಿ
    0.42
     ricerc
    0.42
    ব্রিটিশ
    0.41
     شہری
    0.41
    POSITIVE LOGITS
     and
    0.54
    -
    0.52
     ও
    0.50
     kesehatan
    0.48
     Healthcare
    0.45
     الصحة
    0.44
    and
    0.42
     &
    0.42
     الصحية
    0.41
     healthcare
    0.40
    Act Density 0.002%

    No Known Activations