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

    Neuronpedia

    INDEX
    Explanations

    model response start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seront
    0.46
     physiologic
    0.45
     physiologically
    0.44
     seraient
    0.43
     raster
    0.42
     percussion
    0.42
     retardation
    0.42
     ascertaining
    0.41
     generality
    0.41
     ordinairement
    0.41
    POSITIVE LOGITS
     captivating
    0.44
    `]
    0.42
    !।
    0.41
    有哪些
    0.41
    最新的
    0.40
    ıyoruz
    0.39
     【
    0.39
    PRE
    0.39
    &#
    0.39
    ](#
    0.39
    Act Density 0.502%

    No Known Activations