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

    Neuronpedia

    INDEX
    Explanations

    structured formatting elements in code or text

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

    Code, comments, or markup delimiters

    np_acts-logits-general · gemini-2.0-flash

    textual analysis structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.46
     Great
    -0.42
    turi
    -0.41
    <eos>
    -0.38
    nik
    -0.38
    bootstrapcdn
    -0.37
    icher
    -0.37
     zeker
    -0.37
     
    -0.36
     despe
    -0.35
    POSITIVE LOGITS
    */
    1.32
    */
    1.32
    }*/
    1.32
    });*/
    1.22
    )*/
    1.20
    </h6>
    1.19
     */
    1.18
    );*/
    1.18
     */
    1.15
    </h5>
    1.14
    Act Density 0.284%

    No Known Activations