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

    Neuronpedia

    INDEX
    Explanations

    starts with import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.49
    2
    0.45
    1
    0.42
    your
    0.42
     that
    0.42
     successful
    0.41
     $
    0.41
    that
    0.41
     [
    0.41
     which
    0.41
    POSITIVE LOGITS
     utils
    0.67
     Utils
    0.61
     utilities
    0.60
    Utilities
    0.54
     util
    0.53
     Utilities
    0.53
     json
    0.52
     numpy
    0.52
     io
    0.51
    interfaces
    0.51
    Act Density 0.080%

    No Known Activations