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

    Neuronpedia

    INDEX
    Explanations

    security, mobile, finances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Summit
    0.55
     Telegram
    0.50
     Summit
    0.46
     summits
    0.46
    islava
    0.45
     点击
    0.45
    ialog
    0.43
     Bellamy
    0.43
     Translations
    0.43
    áme
    0.43
    POSITIVE LOGITS
    이면
    0.45
     plex
    0.45
     springing
    0.43
     vrai
    0.43
    湳
    0.41
     choix
    0.41
     سعی
    0.40
     δεν
    0.40
     wary
    0.40
     ایسی
    0.40
    Act Density 0.006%

    No Known Activations