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

    Neuronpedia

    INDEX
    Explanations

    height

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to structural or metadata tokens (e.g. the `<|start_header_id|>` marker) that delineate parts of the document.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prefect
    -0.07
     fruits
    -0.06
    ades
    -0.06
    IRCLE
    -0.06
    え
    -0.06
    ircle
    -0.06
    كار
    -0.06
     cons
    -0.06
     libre
    -0.06
     tsunami
    -0.06
    POSITIVE LOGITS
     Timestamp
    0.07
    .Serializable
    0.07
    BACKGROUND
    0.06
     Trafford
    0.06
    /I
    0.06
     liquidity
    0.06
     VIP
    0.06
     maj
    0.06
     L
    0.06
     _|
    0.06
    Act Density 0.011%

    No Known Activations