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

    Neuronpedia

    INDEX
    Explanations

    overcome obstacles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brahm
    0.47
     rupees
    0.46
     seaw
    0.45
    aadhar
    0.44
     ayurved
    0.43
     rupee
    0.43
     carn
    0.42
     Hindus
    0.41
     saree
    0.41
     dasar
    0.41
    POSITIVE LOGITS
     Ore
    0.43
    Ore
    0.41
    Er
    0.40
    Ros
    0.40
    Ki
    0.38
    キュー
    0.38
    django
    0.38
    伀
    0.37
     Congolese
    0.37
     הבי
    0.37
    Act Density 0.011%

    No Known Activations