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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens—digits and numerical values (including decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hansen
    -0.07
     Lane
    -0.06
     Lyme
    -0.06
     atoms
    -0.06
     motorcycles
    -0.06
    USD
    -0.06
     csv
    -0.06
     eden
    -0.06
    齐
    -0.06
    üssen
    -0.05
    POSITIVE LOGITS
    -multi
    0.07
    restricted
    0.07
    957
    0.07
     substitute
    0.07
    річ
    0.07
     //_
    0.07
    dro
    0.06
     работ
    0.06
     cuz
    0.06
    今日
    0.06
    Act Density 0.010%

    No Known Activations