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

    Neuronpedia

    INDEX
    Explanations

    python module imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hungarian
    0.41
     dihydro
    0.39
    Hung
    0.39
     deferred
    0.37
    VH
    0.36
     lagged
    0.36
     Hung
    0.36
     Hungry
    0.36
    Macrophages
    0.36
     neutralized
    0.36
    POSITIVE LOGITS
     itertools
    0.76
    funct
    0.57
     heapq
    0.55
     hashlib
    0.55
     math
    0.54
     numpy
    0.52
     collections
    0.51
    collections
    0.51
     shutil
    0.51
     модуль
    0.51
    Act Density 0.033%

    No Known Activations