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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash

    Python class definitions related to data handling and serialization.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on lines that import modules (i.e. it detects “import” statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Lin
    -0.07
     applicants
    -0.07
    \Configuration
    -0.06
    -Control
    -0.06
     ENUM
    -0.06
    .signIn
    -0.06
    �
    -0.06
     espacio
    -0.06
    -modules
    -0.06
    ao
    -0.06
    POSITIVE LOGITS
     satur
    0.06
     commodity
    0.06
    lates
    0.06
     Chapter
    0.06
     hesitate
    0.06
     repe
    0.06
     громадян
    0.06
    StorageSync
    0.06
     că
    0.06
    loquent
    0.06
    Act Density 0.006%

    No Known Activations