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

    Neuronpedia

    INDEX
    Explanations

    outdated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.23
    า
    1.16
    ia
    1.14
    .
    1.11
    ā
    0.95
    ित
    0.95
    aren
    0.95
    ა
    0.92
    情况下
    0.91
    eth
    0.91
    POSITIVE LOGITS
    <0x0D>
    1.48
    th
    1.20
    </td>
    1.13
    কে
    1.13
    이었다
    1.13
    0
    1.12
    एम
    1.09
    كان
    1.05
    الأ
    1.05
    czki
    1.05
    Act Density 0.001%

    No Known Activations