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

    Neuronpedia

    INDEX
    Explanations

    code snippets and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =
    0.79
    '
    0.75
    S
    0.75
    ...
    0.75
    "
    0.74
    (
    0.73
    da
    0.73
    ,
    0.72
    -
    0.72
    —
    0.67
    POSITIVE LOGITS
     odnosno
    1.08
     illetve
    1.04
    $-$,
    0.92
     valamint
    0.91
    ?,?,
    0.90
    𒃶
    0.86
     ...)
    0.82
    omitem
    0.82
     andRow
    0.81
     ﺍﻟ
    0.81
    Act Density 0.704%

    No Known Activations