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

    Neuronpedia

    INDEX
    Explanations

    code programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.56
    ↵↵
    0.53
     but
    0.51
    ation
    0.51
    -
    0.48
     and
    0.47
    ing
    0.46
    but
    0.46
     But
    0.44
     ceases
    0.42
    POSITIVE LOGITS
     `${
    0.60
    拃
    0.58
     các
    0.57
     resultArray
    0.57
    MediaQuery
    0.56
    FindFileData
    0.56
     četiri
    0.56
     [{'
    0.56
     {//
    0.55
     "[
    0.55
    Act Density 0.716%

    No Known Activations