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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash

    The neuron activates on quantitative numeric expressions (measurements, percentages, decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    isd
    -0.07
    Name
    -0.07
    .Substring
    -0.07
     getAddress
    -0.07
     conducive
    -0.06
     tcp
    -0.06
     Grimm
    -0.06
      ↵
    -0.06
    _multiply
    -0.06
    (status
    -0.06
    POSITIVE LOGITS
     Blockly
    0.08
     جنوبی
    0.07
    arence
    0.06
    elry
    0.06
     виріш
    0.06
     경찰
    0.06
    هه
    0.06
    λμ
    0.06
     eğer
    0.06
     tieten
    0.06
    Act Density 0.128%

    No Known Activations