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

    Neuronpedia

    INDEX
    Explanations

    ages in medical studies

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (i.e. digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .community
    -0.07
     demonstrations
    -0.07
    (feature
    -0.07
    .retry
    -0.07
    ()._
    -0.06
    gere
    -0.06
    %"
    -0.06
    Report
    -0.06
    assandra
    -0.06
    _Post
    -0.06
    POSITIVE LOGITS
    PH
    0.06
    =>"
    0.06
    (sym
    0.06
     Elig
    0.05
    �
    0.05
    ίδα
    0.05
     },↵↵↵
    0.05
    scope
    0.05
     rules
    0.05
    iev
    0.05
    Act Density 0.003%

    No Known Activations