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

    Neuronpedia

    INDEX
    Explanations

    code syntax, conditions, and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    骖
    0.32
    鄔
    0.31
    欤
    0.29
    軼
    0.29
    퐫
    0.29
    मेरे
    0.29
    ംഗ്
    0.29
    लेरिया
    0.29
    𒁁
    0.29
    मुख
    0.29
    POSITIVE LOGITS
     ...
    0.37
     similarly
    0.37
     /*
    0.34
     '
    0.33
     same
    0.33
     `
    0.33
     <
    0.32
    ...
    0.31
    0.30
     $
    0.30
    Act Density 0.016%

    No Known Activations