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

    Neuronpedia

    INDEX
    Explanations

    ages

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of people’s ages, i.e. numeric tokens in “X-year-old” (or similar) constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     AQ
    -0.07
    (address
    -0.07
    cean
    -0.07
     아닌
    -0.06
    ategorie
    -0.06
    _rot
    -0.06
    .Inst
    -0.06
    běh
    -0.06
     semester
    -0.06
    tener
    -0.06
    POSITIVE LOGITS
     Bool
    0.06
     Often
    0.06
    iệu
    0.06
     �
    0.06
    Scores
    0.06
    latesAutoresizingMaskIntoConstraints
    0.06
     surprises
    0.06
     initComponents
    0.06
     گل
    0.06
     FileName
    0.06
    Act Density 0.021%

    No Known Activations