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

    Neuronpedia

    INDEX
    Explanations

    Institute for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.46
     was
    1.23
    ре
    1.11
    ки
    1.11
    зи
    1.09
    لي
    1.09
    <0xB2>
    1.05
     is
    1.05
    ного
    1.05
     و
    1.04
    POSITIVE LOGITS
    0
    1.17
     Institute
    1.07
    ہ
    1.05
    Institute
    1.03
    이나
    1.02
    𝟬
    1.02
    )(
    1.01
     Institutes
    1.00
    )
    1.00
    ক
    0.99
    Act Density 0.002%

    No Known Activations