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

    Neuronpedia

    INDEX
    Explanations

    portfolio analysis formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lui
    0.47
    ás
    0.46
    ne
    0.45
    atsi
    0.45
    ób
    0.43
     दृष्टी
    0.41
    头
    0.40
    ū
    0.40
     còn
    0.40
    ūt
    0.40
    POSITIVE LOGITS
    Cast
    0.47
    attled
    0.46
     NPD
    0.45
    認知
    0.44
     metac
    0.44
     স্বাস্থ্য
    0.43
    Antaeotricha
    0.43
     geopol
    0.43
    Hasta
    0.43
     burrito
    0.43
    Act Density 0.000%

    No Known Activations