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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric citation or reference markers (the bracketed numbers and other numeric tokens used for citations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    arrass
    -0.06
     가까
    -0.06
     flirting
    -0.06
    Що
    -0.06
     Lawson
    -0.06
     flowed
    -0.06
    iced
    -0.06
    แข
    -0.06
     :-)
    -0.06
    UTTON
    -0.06
    POSITIVE LOGITS
     Nolan
    0.07
    (Parcel
    0.06
     Juni
    0.06
     CompletableFuture
    0.06
     *>
    0.06
    ">↵↵
    0.06
    imagin
    0.06
     вперед
    0.06
    (side
    0.06
    ");}↵
    0.06
    Act Density 0.005%

    No Known Activations