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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting occurrences of the verb “include” (and its forms like “includes” or “including”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     سنوات
    -0.08
    	rm
    -0.07
    sWith
    -0.07
     Granny
    -0.06
     Parliamentary
    -0.06
    _player
    -0.06
    	memcpy
    -0.06
    report
    -0.06
     prism
    -0.06
     هایی
    -0.06
    POSITIVE LOGITS
    essor
    0.07
    	up
    0.06
    ripp
    0.06
    링
    0.06
    olon
    0.06
    tek
    0.06
     integration
    0.06
    ن
    0.06
    ματος
    0.06
    階
    0.06
    Act Density 0.027%

    No Known Activations