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

    Neuronpedia

    INDEX
    Explanations

    latest

    np_max-act · gemini-2.0-flash

    The neuron is activated by software version numbers (e.g. “3.0.45,” “2.0.1,” “latest”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     endeavour
    -0.07
     smaller
    -0.07
     Autism
    -0.07
     eSports
    -0.07
     incidental
    -0.07
     Hazel
    -0.07
    iko
    -0.07
     magical
    -0.06
     Hour
    -0.06
     account
    -0.06
    POSITIVE LOGITS
    	Description
    0.07
     stil
    0.07
    (des
    0.07
     __________________↵↵
    0.07
    scious
    0.07
    DidAppear
    0.07
     ＿
    0.06
    .JsonProperty
    0.06
     ориг
    0.06
     přeh
    0.06
    Act Density 0.014%

    No Known Activations