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

    Neuronpedia

    INDEX
    Explanations

    action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xE2>
    0.17
    ↵↵
    0.16
    ↵
    0.16
    \
    0.16
    -
    0.15
    '
    0.15
     ,
    0.14
    ‍
    0.14
    .
    0.14
    ‌
    0.13
    POSITIVE LOGITS
     the
    0.21
     위의
    0.18
     некоторые
    0.18
     일반
    0.18
     them
    0.16
     अन्य
    0.16
     those
    0.16
     различные
    0.16
     ciertas
    0.16
     these
    0.16
    Act Density 0.558%

    No Known Activations