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

    Neuronpedia

    INDEX
    Explanations

    pygame.display.set_caption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esfuer
    0.54
    讒
    0.47
    वारीत
    0.46
    ما
    0.46
    ٥
    0.46
    क्यात
    0.45
    रिमेंट
    0.45
     ब्लूटूथ
    0.44
    юнча
    0.43
     wład
    0.42
    POSITIVE LOGITS
    ↵↵
    0.50
     ,
    0.46
    0.44
    |
    0.44
    0.43
    \
    0.42
       
    0.42
     |
    0.41
     tr
    0.41
     whatnot
    0.40
    Act Density 0.002%

    No Known Activations