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

    Neuronpedia

    INDEX
    Explanations

    programming-related import statements and references to modules or packages

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

    python imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haikusbot
    -0.59
     كومونز
    -0.58
     InputDecoration
    -0.52
    InstrumentedTest
    -0.51
     ModelRenderer
    -0.51
    WaitGroup
    -0.48
    writeFieldEnd
    -0.47
     للمعارف
    -0.43
    bitField
    -0.42
    MLLoader
    -0.42
    POSITIVE LOGITS
     typing
    0.70
    typing
    0.55
     collections
    0.52
     abstract
    0.51
     abstraction
    0.48
     abstrait
    0.45
     logging
    0.45
    抽象
    0.44
     typed
    0.44
     abc
    0.43
    Act Density 0.007%

    No Known Activations