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

    Neuronpedia

    INDEX
    Explanations

    thread

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of forum discussion threads, especially the word “thread” (and nearby context), indicating it’s looking for references to or headings of discussion threads.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Username
    -0.07
    _properties
    -0.07
     beams
    -0.07
    withdraw
    -0.07
     Tibetan
    -0.07
    ,E
    -0.07
    하면
    -0.07
     cards
    -0.06
     scene
    -0.06
     Writer
    -0.06
    POSITIVE LOGITS
    주
    0.07
    参与
    0.06
     crumbling
    0.06
    的一
    0.06
    COMMENT
    0.06
    ikleri
    0.06
    งเป
    0.06
    .StackTrace
    0.06
    Cách
    0.06
    '))
↵
    0.06
    Act Density 0.010%

    No Known Activations