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

    Neuronpedia

    INDEX
    Explanations

    passing through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لهذه
    0.50
     saling
    0.46
    وت
    0.45
     Auto
    0.45
     diese
    0.44
     tohoto
    0.43
     für
    0.42
     impoz
    0.41
     visar
    0.40
     ऐसे
    0.40
    POSITIVE LOGITS
    ியுடன்
    0.40
    ளுடன்
    0.39
    чном
    0.39
     síndrome
    0.38
    preprocessing
    0.38
    五年
    0.38
    package
    0.37
    arXiv
    0.37
     неожидан
    0.37
    +</
    0.36
    Act Density 0.004%

    No Known Activations