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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash

    technical terms and operations related to programming and software functionalities.

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

    The neuron fires on words and phrases that signal scanning or searching through something (e.g. “look,” “through,” “search,” “iterating”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Utilities
    -0.07
    rine
    -0.07
     setups
    -0.07
    _S
    -0.06
     setup
    -0.06
     ArrayBuffer
    -0.06
    @test
    -0.06
     Cellular
    -0.06
    from
    -0.06
     Cached
    -0.06
    POSITIVE LOGITS
    ằm
    0.06
     darf
    0.06
    IELD
    0.06
    阅读
    0.06
     accounted
    0.06
    '){
    0.06
     Bolshevik
    0.06
    (金
    0.06
     opaque
    0.06
    Annotation
    0.06
    Act Density 0.027%

    No Known Activations