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

    Neuronpedia

    INDEX
    Explanations

    code structure markers and end tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     물질
    0.41
     embroidery
    0.40
     embro
    0.39
    াজ
    0.38
     molécule
    0.38
     ভিতর
    0.38
    ής
    0.37
     Bride
    0.37
     Embro
    0.37
     Blogging
    0.37
    POSITIVE LOGITS
    
    0.52
    ៕
    0.47
    </body>
    0.47
    <0x00>
    0.46
    README
    0.45
    ```
    0.44
    And
    0.43
    `;
    0.42
    
    0.42
    notes
    0.39
    Act Density 0.109%

    No Known Activations