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

    Neuronpedia

    INDEX
    Explanations

    reading order

    np_max-act · gemini-2.0-flash

    The neuron responds to uppercase header or call-out text (e.g. section titles or promotional banners in all caps).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Jennifer
    -0.06
    eing
    -0.06
     ents
    -0.06
    uitka
    -0.06
    Jennifer
    -0.06
    jekt
    -0.06
    Writer
    -0.06
     bones
    -0.06
    (hash
    -0.06
    貸
    -0.06
    POSITIVE LOGITS
    ---@
    0.07
     mouseX
    0.06
    其中
    0.06
     ;;↵
    0.06
    增长
    0.06
     ~
    0.06
    )/(
    0.06
    ~-~-
    0.06
     ~~
    0.06
    **
    0.06
    Act Density 0.051%

    No Known Activations