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

    Neuronpedia

    INDEX
    Explanations

    { and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     burials
    0.44
    蒿
    0.44
     Burial
    0.42
    罾
    0.42
    0.42
    ▲
    0.42
    Against
    0.42
    बान
    0.42
    жні
    0.41
    .​​
    0.41
    POSITIVE LOGITS
     {
    2.67
    {
    2.23
     $\{
    2.19
     \{
    2.08
     $\{\
    2.03
     `{
    1.90
     $\{$
    1.88
     {'
    1.87
    ｛
    1.86
    \{
    1.85
    Act Density 0.177%

    No Known Activations