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

    Neuronpedia

    INDEX
    Explanations

    updating information or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     up
    0.56
     upbringing
    0.46
    起来
    0.45
     outright
    0.45
     uprising
    0.44
     upris
    0.44
    起來
    0.42
     uprisings
    0.42
     onset
    0.42
     употреб
    0.41
    POSITIVE LOGITS
     firmware
    0.49
     propag
    0.48
    SecurityMarks
    0.48
     periodically
    0.46
     régulière
    0.46
     prices
    0.46
     accordingly
    0.45
     régulièrement
    0.45
    iania
    0.45
    颖
    0.45
    Act Density 0.027%

    No Known Activations