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

    Neuronpedia

    INDEX
    Explanations

    "{ or < followed by code/config keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Н
    0.32
    贈り物
    0.31
    ULL
    0.31
    த்தா
    0.30
    Quad
    0.30
    像素
    0.30
    섦
    0.30
     predicate
    0.30
    ساب
    0.30
     ikan
    0.30
    POSITIVE LOGITS
     اح
    0.44
    0.38
     অন্যান্য
    0.37
     ArrayList
    0.35
    0.35
     nhiệm
    0.34
     ð
    0.34
     eventuali
    0.34
     ଗ
    0.34
    0.33
    Act Density 0.005%

    No Known Activations