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

    Neuronpedia

    INDEX
    Explanations

    end punctuation followed by dash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     、,
    0.87
     $(*
    0.83
    (?:
    0.76
    ("/{
    0.75
     。,
    0.75
    etc
    0.70
     $\$
    0.69
    ([^
    0.68
    吅
    0.68
    (),"
    0.67
    POSITIVE LOGITS
     –
    5.30
     -
    4.69
     —
    4.39
    —
    4.01
     --
    3.94
    –
    3.70
     −
    3.37
    --
    3.28
     －
    3.14
     $-$
    3.11
    Act Density 5.697%

    No Known Activations