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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash

    This neuron activates on the Python‐style regex named‐capture‐group syntax sequences “(?P<…>” in regular expression patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     devout
    -0.07
    Html
    -0.07
     corpor
    -0.07
    both
    -0.06
     eminent
    -0.06
     ambos
    -0.06
    jquery
    -0.06
    approx
    -0.06
     κου
    -0.06
    .listBox
    -0.06
    POSITIVE LOGITS
    acie
    0.07
     qint
    0.07
    getic
    0.07
     Test
    0.07
     choice
    0.07
     Processing
    0.06
    断
    0.06
    .mit
    0.06
     automated
    0.06
     떨어
    0.06
    Act Density 0.001%

    No Known Activations