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

    Neuronpedia

    INDEX
    Explanations

    subject matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nowoczes
    0.44
     дизайне
    0.41
    ஜ்மஹால்
    0.40
     আফজাল
    0.39
     çalışmaları
    0.39
     форми
    0.38
     홈페이지
    0.38
     теку
    0.38
     geniş
    0.38
     атом
    0.38
    POSITIVE LOGITS
    计
    0.44
    蓝
    0.43
     blue
    0.42
    blue
    0.40
    violations
    0.39
    Concern
    0.39
    诿
    0.39
    勒
    0.38
    يميديا
    0.37
     सारा
    0.37
    Act Density 0.002%

    No Known Activations