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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    `.
    0.70
    `;
    0.64
    `)
    0.60
     `;
    0.59
    ``.
    0.57
    ```
    0.56
    }`
    0.55
    ``
    0.53
    `).
    0.52
    .`
    0.52
    POSITIVE LOGITS
    ."—
    0.51
     demie
    0.46
    !">
    0.46
    "){
    0.45
    重要な
    0.45
    Biographie
    0.43
    \">\
    0.43
    ")){
    0.42
    ?",
    0.41
     }}(\
    0.41
    Act Density 0.137%

    No Known Activations