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

    Neuronpedia

    INDEX
    Explanations

    Dates and numbers

    np_max-act · gemini-2.0-flash

    the neuron detects numeric tokens, especially years and other multi-digit dates/numbers.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Pane
    -0.08
     sito
    -0.08
     organizations
    -0.07
     Monitoring
    -0.07
    /UIKit
    -0.07
    EmptyEntries
    -0.07
     Fonts
    -0.07
    .ImageView
    -0.07
     Ağustos
    -0.07
     enterprises
    -0.07
    POSITIVE LOGITS
    掉
    0.08
    formed
    0.07
    抵挡
    0.07
    🤞
    0.07
     predictable
    0.07
     ()=>
    0.07
     abound
    0.06
    。。。
    0.06
    .Handle
    0.06
    却
    0.06
    Act Density 0.051%

    No Known Activations