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

    Neuronpedia

    INDEX
    Explanations

    furious and Julius

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቺ
    -3.00
    ጺ
    -2.83
    ዡ
    -2.80
     всѣ
    -2.69
    ቬ
    -2.61
    ዒ
    -2.61
    -2.58
    -2.56
    橚
    -2.56
     recomendaciones
    -2.55
    POSITIVE LOGITS
    .
    5.19
    that
    2.92
    ity
    2.73
    ,
    2.66
    }
    2.61
     что
    2.56
     but
    2.48
    в
    2.44
     没有
    2.34
     That
    2.33
    Act Density 0.002%

    No Known Activations