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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—court citations, docket or rule numbers, years, and decimal figures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    เหมาะ
    -0.07
     정말
    -0.06
     appreciation
    -0.06
    рез
    -0.06
    oload
    -0.06
    _async
    -0.06
     onPostExecute
    -0.06
    Hundreds
    -0.06
     deem
    -0.06
    Textbox
    -0.06
    POSITIVE LOGITS
    _traffic
    0.07
    ाइड
    0.07
     wrongdoing
    0.07
    urniture
    0.06
     notifying
    0.06
    rapped
    0.06
    FONT
    0.06
     Outdoor
    0.06
    (origin
    0.06
     році
    0.06
    Act Density 0.002%

    No Known Activations