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

    Neuronpedia

    INDEX
    Explanations

    definitions and terminology

    np_max-act · gemini-2.0-flash

    The neuron detects introductory or explanatory phrases that lead into a list or define how to interpret list items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Grande
    -0.07
     Walsh
    -0.07
    uje
    -0.07
     Lightweight
    -0.06
     编辑
    -0.06
     luxe
    -0.06
     acknowledging
    -0.06
    ów
    -0.06
    Numero
    -0.06
    enty
    -0.06
    POSITIVE LOGITS
     Giov
    0.06
    	Date
    0.06
    Concurrency
    0.06
    WebResponse
    0.06
     LINK
    0.06
    lland
    0.06
     *)[
    0.06
     poverty
    0.05
     harb
    0.05
     ژاپ
    0.05
    Act Density 0.198%

    No Known Activations