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

    Neuronpedia

    INDEX
    Explanations

    certain cancers, macular degeneration, excel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    았던
    0.44
     বির
    0.42
    ગવાન
    0.41
     unary
    0.40
    簷
    0.40
     ميل
    0.40
    (",");
    0.40
    趸
    0.40
    並且
    0.40
     重量
    0.40
    POSITIVE LOGITS
    </strong>
    0.44
     That
    0.42
    that
    0.42
     iletişim
    0.41
    دانلود
    0.40
    Were
    0.40
    </b>
    0.40
    இந்த
    0.39
    for
    0.38
     Applying
    0.38
    Act Density 0.003%

    No Known Activations