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

    Neuronpedia

    INDEX
    Explanations

    sentence punctuation and short words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h3>
    0.95
    ...')
    0.94
     ..."
    0.86
     expts
    0.82
    …"
    0.82
    ວກ
    0.80
    ახებ
    0.79
     \...
    0.78
    ･･･
    0.78
    ?')
    0.78
    POSITIVE LOGITS
    ​
    1.62
    ​,
    1.51
    ⁣
    1.45
    ⁤
    1.45
    ,​
    1.42
     ​
    1.39
    ⁢
    1.36
    ​.
    1.31
    ‏
    1.29
    -​
    1.29
    Act Density 1.704%

    No Known Activations