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

    Neuronpedia

    INDEX
    Explanations

    Expected X but was Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offsetX
    0.34
    fireFlower
    0.34
     bioactive
    0.33
    梼
    0.33
     elementType
    0.32
     stratigraphic
    0.32
    沍
    0.32
     trycatch
    0.31
     halfCanvas
    0.31
    หมือน
    0.31
    POSITIVE LOGITS
    -
    0.36
    ↵
    0.32
    *
    0.29
    .
    0.29
    an
    0.28
    al
    0.28
    at
    0.28
    pl
    0.28
    am
    0.28
    '
    0.27
    Act Density 0.000%

    No Known Activations