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

    Neuronpedia

    INDEX
    Explanations

    specialized symbols or formatting elements in the document

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

    Code-related syntax and characters

    np_acts-logits-general · gemini-2.0-flash

    code blocks and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    twimg
    -0.63
    Datuak
    -0.61
    AllAfrica
    -0.55
     Italijani
    -0.54
     lenker
    -0.54
     oligo
    -0.53
    jsoup
    -0.52
    uscitation
    -0.52
    endsection
    -0.52
    Viki
    -0.52
    POSITIVE LOGITS
    </h5>
    0.78
    </h4>
    0.77
    </em>
    0.72
    </u>
    0.65
    </h6>
    0.63
    });*/
    0.62
    </h2>
    0.62
    </strong>
    0.61
    </i>
    0.61
    })*/
    0.59
    Act Density 0.069%

    No Known Activations