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

    Neuronpedia

    INDEX
    Explanations

    artificial intelligence

    np_max-act · gemini-2.0-flash

    This neuron detects tokens marking or occurring in the user‐side message header and start of a user question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (year
    -0.08
    sitemap
    -0.06
    Segments
    -0.06
    Marker
    -0.06
     　　 　
    -0.06
    ↵        
↵
    -0.06
     championships
    -0.06
    fifo
    -0.06
    .borderColor
    -0.06
     UIScreen
    -0.06
    POSITIVE LOGITS
     fired
    0.07
    sending
    0.06
    pun
    0.06
    ibrary
    0.06
    crew
    0.06
     için
    0.06
     mysl
    0.06
     trest
    0.06
     Crypt
    0.06
     boss
    0.06
    Act Density 0.035%

    No Known Activations