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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on “from” keywords that begin import statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <Audio
    -0.07
     cinema
    -0.06
    (file
    -0.06
     DAYS
    -0.06
    (OS
    -0.06
    "+
    -0.06
     Holly
    -0.06
    ;\
    -0.06
     owe
    -0.06
    (name
    -0.06
    POSITIVE LOGITS
     XCTAssertTrue
    0.06
    @RestController
    0.06
     cupboard
    0.06
     Amerikan
    0.06
    iciar
    0.06
    ")]
    0.06
     NotImplemented
    0.06
     immune
    0.06
     Οι
    0.06
     painted
    0.06
    Act Density 0.003%

    No Known Activations