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

    Neuronpedia

    INDEX
    Explanations

    Historical revisionism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Panic
    0.45
    ிகு
    0.43
    Panic
    0.42
    Catch
    0.41
     ক্রস
    0.41
     Worry
    0.40
    ፕ
    0.39
     tracker
    0.39
    Tracking
    0.39
    有望
    0.39
    POSITIVE LOGITS
     revision
    1.08
     histori
    1.07
    revision
    1.02
     whitew
    0.98
     historians
    0.98
     rewriting
    0.93
     इतिहासकारों
    0.93
     Histor
    0.93
     historian
    0.93
     Revision
    0.90
    Act Density 0.012%

    No Known Activations