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

    Neuronpedia

    INDEX
    Explanations

    Years and awards

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to numeric tokens—especially years—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _impl
    -0.06
    _Level
    -0.06
    Nothing
    -0.06
     Ella
    -0.06
    Finance
    -0.06
    	Update
    -0.06
     '\"
    -0.06
     barley
    -0.06
    (schedule
    -0.06
     UserDefaults
    -0.06
    POSITIVE LOGITS
     catalogs
    0.07
    #w
    0.07
     Ülke
    0.07
     Conn
    0.06
    lined
    0.06
     celebrated
    0.06
    ۱۹۶
    0.06
    .ensure
    0.06
    _child
    0.06
    !");↵↵
    0.06
    Act Density 0.012%

    No Known Activations