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

    Neuronpedia

    INDEX
    Explanations

    genetic polymorphisms

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects numerical tokens (e.g. percentages, decimals, rs-IDs, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Loch
    -0.06
     Perception
    -0.06
    =_
    -0.06
    colm
    -0.06
    lec
    -0.06
    Meg
    -0.06
     Topic
    -0.06
    Sense
    -0.06
    .Mock
    -0.06
    xor
    -0.06
    POSITIVE LOGITS
     grou
    0.07
    snippet
    0.06
     WX
    0.06
     converts
    0.06
     guarding
    0.06
     drei
    0.06
     sucker
    0.06
     pojist
    0.06
     fazla
    0.06
    ристи
    0.06
    Act Density 0.017%

    No Known Activations