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

    Neuronpedia

    INDEX
    Explanations

    National Strat tricky Lancet People

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    윙
    0.75
     licensee
    0.72
     ম্যাজিস্ট
    0.72
     Flinders
    0.70
    鵡
    0.69
     overhang
    0.67
    चु
    0.66
    管理器
    0.66
     ನೇ
    0.66
     прямо
    0.66
    POSITIVE LOGITS
     exercitation
    0.79
    Что
    0.78
    ഗ്
    0.76
     Италии
    0.74
    രീ
    0.74
    Regional
    0.74
     عندهم
    0.73
     نړ
    0.73
    http
    0.72
    心里
    0.71
    Act Density 0.001%

    No Known Activations