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

    Neuronpedia

    INDEX
    Explanations

    python code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    髗
    0.42
    毆
    0.42
    ၣ်
    0.41
    tFileInputExcel
    0.40
    DataXYZ
    0.40
     समुदा
    0.38
    стро
    0.38
     ನೇ
    0.38
    ançois
    0.38
     तरल
    0.38
    POSITIVE LOGITS
    ↵
    0.43
     ,
    0.42
    ้
    0.40
     .
    0.40
    et
    0.40
    能
    0.39
    ↵↵
    0.38
    е
    0.37
    ↵↵↵
    0.37
    டும்
    0.37
    Act Density 0.010%

    No Known Activations