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

    Neuronpedia

    INDEX
    Explanations

    definitions and code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    براير
    0.53
    nashvillehousing
    0.47
    𒃻
    0.46
    elevationMap
    0.46
     prestasi
    0.46
    পালের
    0.46
    窸
    0.45
    <unused1848>
    0.45
    ষণের
    0.45
    OLYBD
    0.44
    POSITIVE LOGITS
     =
    0.77
    _
    0.66
    =
    0.65
    /
    0.64
    ,
    0.63
     {
    0.60
    (
    0.57
    {
    0.57
    \
    0.57
    l
    0.56
    Act Density 0.012%

    No Known Activations