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

    Neuronpedia

    INDEX
    Explanations

    JSON structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‘
    0.83
    :)
    0.81
     (‘
    0.80
    ;)
    0.80
     ‘
    0.75
    :-)
    0.74
    ROI
    0.73
    ('./
    0.73
    (=
    0.69
    0.69
    POSITIVE LOGITS
     [],
    1.77
     null
    1.51
     "",
    1.47
     {},
    1.35
    null
    1.34
     "-",
    1.22
    [],
    1.20
     ",",
    1.15
     ".",
    1.12
     false
    1.08
    Act Density 0.233%

    No Known Activations