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

    Neuronpedia

    INDEX
    Explanations

    distributed copies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دیے
    0.42
     العشر
    0.41
    हायला
    0.39
    りの
    0.39
     refinements
    0.38
    ه‌
    0.38
     طيب
    0.38
     phospholipids
    0.38
     оптими
    0.37
     (’
    0.37
    POSITIVE LOGITS
    嬂
    0.47
     Asiatic
    0.44
     torn
    0.43
     glossy
    0.39
     ரசிக
    0.38
    羪
    0.37
     budget
    0.37
    chedule
    0.37
    etik
    0.37
    严格
    0.36
    Act Density 0.005%

    No Known Activations