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

    Neuronpedia

    INDEX
    Explanations

    Statistical significance values

    np_max-act · gemini-2.0-flash

    phrases related to medical study design and findings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects decimal‐formatted numerical tokens used in statistical reporting—e.g. P-values, percentages, confidence intervals, hazard ratios, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     incapac
    -0.06
     Processes
    -0.06
     Paste
    -0.06
     twig
    -0.05
     جز
    -0.05
    、​
    -0.05
    fect
    -0.05
     grabbed
    -0.05
     niveau
    -0.05
    نب
    -0.05
    POSITIVE LOGITS
    toArray
    0.07
    со
    0.07
     달
    0.07
    _raw
    0.06
    _len
    0.06
    tone
    0.06
     Cinema
    0.06
     dood
    0.06
    ardo
    0.06
    ="../../
    0.06
    Act Density 0.004%

    No Known Activations