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

    Neuronpedia

    INDEX
    Explanations

    Python imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pyrid
    0.64
    $\
    0.62
    />
    0.61
    BatchNorm
    0.60
    [-\
    0.60
    から
    0.58
    Bel
    0.58
    Tenn
    0.58
    °
    0.58
    Quer
    0.58
    POSITIVE LOGITS
     datetime
    0.90
     typing
    0.88
     collections
    0.82
     .
    0.81
     urllib
    0.79
     funct
    0.76
     ۱۵
    0.74
     pathlib
    0.70
     decimal
    0.70
     abc
    0.68
    Act Density 0.027%

    No Known Activations