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

    Neuronpedia

    INDEX
    Explanations

    html and script tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {
    0.86
    {
    0.79
     Those
    0.75
    岖
    0.74
     gây
    0.71
     `%
    0.71
     Home
    0.71
     (+
    0.70
     в
    0.70
     heartburn
    0.69
    POSITIVE LOGITS
    br
    1.27
    Br
    1.10
    pre
    1.09
    excludeFolder
    1.05
    ovec
    1.03
    tex
    0.98
    templat
    0.96
    div
    0.94
    wbr
    0.92
    span
    0.91
    Act Density 0.071%

    No Known Activations