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

    Neuronpedia

    INDEX
    Explanations

    punctuation and list delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ccccc
    0.46
     *\
    0.38
    igure
    0.37
    ────────
    0.37
    cvtColor
    0.36
     summers
    0.35
     желу
    0.35
     backyard
    0.34
    基本上
    0.34
     punctuation
    0.34
    POSITIVE LOGITS
     ,
    0.63
     ,,
    0.59
     "",
    0.55
    ,,,
    0.53
     [],
    0.52
     “”
    0.52
     _,
    0.50
    _,
    0.49
     (),
    0.49
    [],
    0.48
    Act Density 0.018%

    No Known Activations