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

    Neuronpedia

    INDEX
    Explanations

    results

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric values (especially decimal or floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     phrases
    -0.06
     roofs
    -0.06
    สาม
    -0.06
     houses
    -0.06
     (("
    -0.06
    ambre
    -0.06
    /style
    -0.06
    Ur
    -0.06
    AR
    -0.06
     Heart
    -0.06
    POSITIVE LOGITS
    _nums
    0.08
    :variables
    0.07
     Univers
    0.07
    езульт
    0.07
    ją
    0.07
     kaz
    0.07
     Ortiz
    0.07
     unfairly
    0.07
     simply
    0.07
     leggings
    0.07
    Act Density 0.025%

    No Known Activations