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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .'),
    0.57
    *****",
    0.56
     petrochemical
    0.55
    ждены
    0.54
     लेणी
    0.54
     '),
    0.53
     따르면
    0.52
     }}=\
    0.51
    ."),
    0.51
     ****",
    0.51
    POSITIVE LOGITS
    </body>
    0.93
    </div>
    0.87
    </ul>
    0.82
    </html>
    0.76
    </tr>
    0.75
    endif
    0.74
    </table>
    0.72
    </tbody>
    0.72
    end
    0.72
    </td>
    0.71
    Act Density 0.245%

    No Known Activations