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

    Neuronpedia

    INDEX
    Explanations

    lists, code, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺭ
    0.48
    prise
    0.46
    ार्थ
    0.46
     没有
    0.45
     الموافق
    0.45
    दिनी
    0.45
     می‌کن
    0.44
    Ր
    0.44
    ními
    0.44
    ﺁ
    0.44
    POSITIVE LOGITS
    푐
    0.61
    >
    0.52
    ักษณะ
    0.50
     \
    0.50
            
    0.48
    When
    0.48
    0.48
              
    0.47
    2
    0.47
    ];
    0.46
    Act Density 0.128%

    No Known Activations