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

    Neuronpedia

    INDEX
    Explanations

    closing head tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     girder
    0.49
     डिवा
    0.43
     soliton
    0.43
    ὺς
    0.42
     discretized
    0.42
    Seqs
    0.42
    Butyl
    0.42
    शिलाजीत
    0.41
    cery
    0.41
     divisional
    0.41
    POSITIVE LOGITS
    <li>
    0.82
    <body>
    0.79
    <tr>
    0.60
    <td>
    0.59
    li
    0.57
    lı
    0.54
    </html>
    0.52
     li
    0.52
    html
    0.50
     body
    0.49
    Act Density 0.016%

    No Known Activations