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

    Neuronpedia

    INDEX
    Explanations

    code structures or parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ra
    0.41
    ya
    0.39
    if
    0.39
    ary
    0.39
    array
    0.39
    utf
    0.39
    ods
    0.38
    ram
    0.38
    do
    0.38
    huang
    0.38
    POSITIVE LOGITS
     (
    0.75
    简称
    0.73
     abbreviated
    0.69
     $(\
    0.67
    (
    0.64
    '(
    0.63
    ("
    0.61
     (“
    0.61
     ('
    0.60
     ("
    0.60
    Act Density 0.104%

    No Known Activations