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

    Neuronpedia

    INDEX
    Explanations

    power dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.68
    นั่ง
    0.64
    ↵↵
    0.62
    ograma
    0.62
     La
    0.61
     coup
    0.61
     news
    0.60
    ‌
    0.58
    HOW
    0.58
     pana
    0.57
    POSITIVE LOGITS
    毉
    0.98
    萛
    0.93
    ့်
    0.90
    жной
    0.89
     beragam
    0.89
    偻
    0.88
     eigenvectors
    0.86
    愘
    0.86
     большой
    0.84
     Moskau
    0.84
    Act Density 0.000%

    No Known Activations