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

    Neuronpedia

    INDEX
    Explanations

    code, symbols, assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slice
    0.80
     slices
    0.78
    Slice
    0.78
    slices
    0.72
     Slice
    0.70
    slice
    0.62
     slicing
    0.59
     sliced
    0.55
    SLICE
    0.54
     slic
    0.52
    POSITIVE LOGITS
     &
    0.59
    &
    0.47
    (&
    0.44
    =&
    0.44
    &$
    0.44
     (&
    0.43
    &+
    0.41
    >&
    0.40
    oauth
    0.39
    ＆
    0.39
    Act Density 0.006%

    No Known Activations