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

    Neuronpedia

    INDEX
    Explanations

    html tags and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recursion
    0.85
     header
    0.78
     main
    0.78
    </thead>
    0.77
     ט
    0.75
     fuselage
    0.75
     tortured
    0.74
    蕪
    0.74
     καν
    0.73
     `.
    0.72
    POSITIVE LOGITS
    br
    1.47
    p
    1.12
    span
    1.02
    Br
    1.01
    BR
    0.98
     br
    0.96
    img
    0.96
    para
    0.93
    font
    0.91
    bold
    0.89
    Act Density 0.037%

    No Known Activations