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

    Neuronpedia

    INDEX
    Explanations

    end-of-line comment indicators in code

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

    code comments and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ième
    -0.51
     isSet
    -0.41
     Bekasi
    -0.40
     Tangerang
    -0.40
     Uribe
    -0.38
     igång
    -0.37
     becauſe
    -0.36
     kazak
    -0.36
     battu
    -0.36
     faune
    -0.36
    POSITIVE LOGITS
     */
    1.25
    */
    0.93
    <bos>
    0.90
    
    0.88
     */
    0.86
    ]));
    0.82
    }));
    0.82
     """
    0.82
     ")
    0.79
    }")
    0.79
    Act Density 0.001%

    No Known Activations