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

    Neuronpedia

    INDEX
    Explanations

    "Issues"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.33
    <unused2221>
    0.33
    ,
    0.31
    <unused2130>
    0.30
    `
    0.30
    [^
    0.28
    .
    0.28
    <unused100>
    0.28
    -
    0.28
     significantly
    0.27
    POSITIVE LOGITS
     উহার
    0.32
     Owing
    0.32
     inoltre
    0.31
     ইহাতে
    0.31
     ইহার
    0.30
     উহা
    0.30
     aforesaid
    0.30
     গিয়াছে
    0.30
     রহিয়াছে
    0.30
     কিরূপে
    0.30
    Act Density 9.272%

    No Known Activations