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

    Neuronpedia

    INDEX
    Explanations

    NER tags and code structuring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Фи
    0.91
     liegen
    0.88
     laborales
    0.88
    이면
    0.87
    ил
    0.86
     สืบค้น
    0.86
    ्रल
    0.86
    you
    0.84
     চাহিয়া
    0.83
    ర్‌
    0.83
    POSITIVE LOGITS
    }},
    0.78
    слава
    0.72
     école
    0.71
    "="
    0.70
    }}^{
    0.68
    }]},
    0.66
    )}}
    0.64
     })}
    0.64
    ⑸
    0.64
    0.64
    Act Density 0.000%

    No Known Activations