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

    Neuronpedia

    INDEX
    Explanations

    immediate context or surroundings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.38
    ’
    1.23
    olie
    1.16
    -
    1.16
    yl
    1.16
    üm
    1.15
    är
    1.13
    ICK
    1.13
    ř
    1.13
    olit
    1.11
    POSITIVE LOGITS
    ع
    1.72
    ле
    1.36
    м
    1.23
     for
    1.23
    ่า
    1.17
    ف
    1.16
    to
    1.13
    е
    1.10
    ки
    1.07
    ح
    1.05
    Act Density 0.018%

    No Known Activations