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

    Neuronpedia

    INDEX
    Explanations

    Code/technical snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on punctuation and other non‐word tokens (commas, periods, quotes, parentheses, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     시장
    -0.08
    VIDEO
    -0.07
     Started
    -0.07
    YouTube
    -0.07
     Miner
    -0.07
    (GTK
    -0.06
     QUERY
    -0.06
     bears
    -0.06
     Playstation
    -0.06
     porad
    -0.06
    POSITIVE LOGITS
    ,function
    0.06
    /Common
    0.06
     土
    0.06
    mus
    0.06
     dříve
    0.05
    属于
    0.05
    hostname
    0.05
    مارات
    0.05
    olders
    0.05
    (hero
    0.05
    Act Density 0.085%

    No Known Activations