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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ながら
    0.43
     WHILE
    0.41
    Mientras
    0.41
     меда
    0.41
    ພວກເຮົາ
    0.40
    ównie
    0.39
    轳
    0.39
    ionalmente
    0.39
    ଐ
    0.38
    MORDOR
    0.38
    POSITIVE LOGITS
    ↵
    0.46
    bool
    0.44
    ↵↵↵
    0.44
    ↵↵
    0.42
    //=
    0.38
     bool
    0.38
     loads
    0.37
    ,
    0.37
     mogu
    0.37
     কাটা
    0.37
    Act Density 0.020%

    No Known Activations