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

    Neuronpedia

    INDEX
    Explanations

    so far and until now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annually
    0.80
     ఉండే
    0.77
     তৎকালীন
    0.76
     máxima
    0.70
     kullanılır
    0.68
     geschikt
    0.68
    hiyan
    0.68
     pinn
    0.68
    เหมาะ
    0.67
    atown
    0.67
    POSITIVE LOGITS
     bisher
    2.54
     지금까지
    2.35
     இதுவரை
    2.28
     bislang
    2.08
     already
    1.97
    迄
    1.97
     تاک
    1.90
     Already
    1.87
    Already
    1.85
    到现在
    1.85
    Act Density 0.196%

    No Known Activations