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

    Neuronpedia

    INDEX
    Explanations

    200, 201

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to four-digit year tokens (dates) in the legal-text citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Floating
    -0.06
     menos
    -0.06
    ikers
    -0.06
    istribution
    -0.06
    (pattern
    -0.06
     business
    -0.06
     temperament
    -0.06
    (channel
    -0.06
     racing
    -0.06
    phabet
    -0.06
    POSITIVE LOGITS
     vehement
    0.07
     :/:
    0.07
     pathMatch
    0.06
     ;;^
    0.06
    ')?>
    0.06
     provoc
    0.06
    fec
    0.06
     eskorte
    0.06
     JMenuItem
    0.06
    <Comment
    0.06
    Act Density 0.026%

    No Known Activations