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

    Neuronpedia

    INDEX
    Explanations

    code interpolation and templating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )...
    0.75
    ...")
    0.68
     Township
    0.67
     alanine
    0.65
     its
    0.65
     радо
    0.63
     girdle
    0.62
    ）」
    0.62
     marks
    0.62
    采集
    0.61
    POSITIVE LOGITS
    ${
    1.07
    {
    1.06
    %
    0.99
     %
    0.99
    {$
    0.89
     {
    0.87
    $%
    0.87
     $\%
    0.85
    +{
    0.84
     "%
    0.83
    Act Density 0.203%

    No Known Activations