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

    Neuronpedia

    INDEX
    Explanations

    code comments and blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lö
    0.74
    PVC
    0.72
    年輕
    0.70
    }^{-\
    0.70
    witz
    0.70
    $-[
    0.69
    ratic
    0.69
    年轻
    0.68
    ChoiceItemLayout
    0.68
     सहार
    0.68
    POSITIVE LOGITS
     //
    1.06
    //
    1.00
    <0x0D>
    0.98
    ↵
    0.88
    )//
    0.83
    {
    0.75
     //-
    0.73
     {
    0.72
    ｛
    0.71
    //"
    0.68
    Act Density 0.157%

    No Known Activations