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

    Neuronpedia

    INDEX
    Explanations

    leetcode.com references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ди
    1.06
    л
    1.03
    ва
    0.91
    다
    0.83
     be
    0.77
    ях
    0.77
    ोत
    0.77
    к
    0.77
     кораб
    0.76
    و
    0.75
    POSITIVE LOGITS
    }{
    0.99
    </h3>
    0.86
    ↵
    0.86
    </h5>
    0.78
    -
    0.77
    '
    0.77
    )।
    0.75
    買った
    0.73
    F
    0.72
    </h2>
    0.68
    Act Density 0.000%

    No Known Activations