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

    Neuronpedia

    INDEX
    Explanations

    United States

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (numbers, percentages, and decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Parsing
    -0.06
    (fake
    -0.06
     sung
    -0.06
    _activity
    -0.06
     pet
    -0.06
     parameter
    -0.06
     supporter
    -0.06
    _STORAGE
    -0.06
    _RANK
    -0.06
    Authorization
    -0.06
    POSITIVE LOGITS
     damning
    0.07
    fram
    0.07
     USSR
    0.06
    イス
    0.06
    ıb
    0.06
     короб
    0.06
     vitam
    0.06
     víde
    0.06
    itic
    0.06
     docks
    0.06
    Act Density 0.035%

    No Known Activations