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

    Neuronpedia

    INDEX
    Explanations

    lists separated by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    텨
    0.68
    ಶ್
    0.65
    тып
    0.64
    ctomy
    0.63
    ysel
    0.63
     चंद्रशेखर
    0.61
    าค
    0.61
    和大
    0.60
     normalization
    0.59
     कराया
    0.58
    POSITIVE LOGITS
    ↵↵
    1.21
    ↵
    0.95
    ↵↵↵
    0.86
     chinois
    0.84
    </ul>
    0.84
     Perhaps
    0.83
     There
    0.80
     Sticker
    0.80
     Thank
    0.80
     :)
    0.79
    Act Density 0.070%

    No Known Activations