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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exter
    0.71
    imut
    0.71
     Premises
    0.69
    ம்பிய
    0.68
     Hauser
    0.67
    ეგის
    0.67
     roundabout
    0.66
    楽天市場
    0.66
     authorities
    0.65
    enge
    0.64
    POSITIVE LOGITS
    </h4>
    1.76
    </h6>
    0.94
    </th>
    0.87
    </h3>
    0.77
    </h1>
    0.77
    </u>
    0.76
    ");
    0.73
    </sub>
    0.73
    </h2>
    0.65
     %}
    0.65
    Act Density 0.000%

    No Known Activations