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

    Neuronpedia

    INDEX
    Explanations

    code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lucas
    0.39
    $}}
    0.38
    />}
    0.37
     adelant
    0.36
    创造
    0.36
    ंतर
    0.36
    িকল্প
    0.36
     качество
    0.36
     ইসলামী
    0.36
    あった
    0.35
    POSITIVE LOGITS
     ]:
    0.43
     ");
    0.37
    ll
    0.37
    itu
    0.36
     )$
    0.36
    )`;
    0.35
     ]);
    0.35
     ];
    0.34
     ):
    0.34
    ++);
    0.34
    Act Density 0.008%

    No Known Activations