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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on common English function words—short articles, prepositions, and conjunctions such as “in,” “the,” and “and.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    T
    -0.07
    .structure
    -0.07
    one
    -0.07
     nen
    -0.06
     Mill
    -0.06
     EACH
    -0.06
     cock
    -0.06
     那
    -0.06
    999
    -0.06
    tae
    -0.06
    POSITIVE LOGITS
    .
    0.08
     ).
    0.07
    paredStatement
    0.07
    ("");↵↵
    0.06
     ">↵
    0.06
    ].
    0.06
     "//
    0.06
    ")).
    0.06
    URIComponent
    0.06
    ','"+
    0.06
    Act Density 0.015%

    No Known Activations