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

    Neuronpedia

    INDEX
    Explanations

    action verbs and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这种
    0.42
    这样一个
    0.40
    and
    0.38
    했던
    0.38
     അയാൾ
    0.38
    और
    0.38
     aquele
    0.38
    性和
    0.37
    在我们
    0.37
     барои
    0.36
    POSITIVE LOGITS
    .
    0.47
    。『
    0.47
    ។
    0.47
    ।
    0.45
    న్నారు
    0.44
    ↵↵
    0.43
    ؛
    0.42
    ‪
    0.42
    😢
    0.42
    །
    0.41
    Act Density 0.231%

    No Known Activations