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

    Neuronpedia

    INDEX
    Explanations

    essay, e-commerce, e.g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    larda
    2.64
    tól
    2.25
    تها
    2.19
    stones
    2.17
     источ
    2.13
    ture
    2.09
    n
    2.09
    más
    2.08
    nj
    2.06
    től
    2.06
    POSITIVE LOGITS
    ю
    2.14
    и
    1.88
    ри
    1.83
    ш
    1.80
    с
    1.79
    š
    1.67
    খানি
    1.64
    ท์
    1.64
    ব
    1.59
    ർ
    1.56
    Act Density 0.281%

    No Known Activations