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

    Neuronpedia

    INDEX
    Explanations

    patterns of underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or comments within PHP code

    np_acts-logits-general · gemini-2.0-flash

    code comments and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.72
    NameInMap
    -0.68
    ViewImports
    -0.60
    __':
    -0.59
    ConstraintMaker
    -0.58
    rizona
    -0.56
     resourceCulture
    -0.56
    клопе
    -0.56
     linkovi
    -0.55
    Extinguishing
    -0.55
    POSITIVE LOGITS
     */
    0.82
    */
    0.80
    </blockquote>
    0.73
    </code>
    0.65
    </tr>
    0.60
    </em>
    0.57
    EndInit
    0.55
    verwijspagina
    0.53
    </td>
    0.51
    </tbody>
    0.50
    Act Density 0.032%

    No Known Activations