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

    Neuronpedia

    INDEX
    Explanations

    references to programming frameworks and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    MongoClient connect and then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.49
    ylvan
    -0.44
    cjon
    -0.41
    unistd
    -0.37
    izient
    -0.37
     camp
    -0.36
    Cela
    -0.35
     spandex
    -0.35
    tdessen
    -0.35
    Aggregate
    -0.35
    POSITIVE LOGITS
    jsxFileName
    0.72
     resourceCulture
    0.60
    tslib
    0.55
     estekak
    0.52
     виправивши
    0.51
    RegressionTest
    0.50
    ArgumentParser
    0.50
    riwal
    0.50
    хьтан
    0.49
    ModelSerializer
    0.49
    Act Density 0.000%

    No Known Activations