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

    Neuronpedia

    INDEX
    Explanations

    URLs and blog posts

    np_max-act · gemini-2.0-flash

    ways to express gratitude or acknowledgment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on numeric ID segments in URLs (e.g. path components like “205”, “253”, “518”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ()].
    -0.07
    ẳng
    -0.06
     spree
    -0.06
    osal
    -0.06
    .rc
    -0.06
    ества
    -0.06
    _CUBE
    -0.06
    .config
    -0.06
     chassis
    -0.06
     Suite
    -0.06
    POSITIVE LOGITS
    /private
    0.06
    -share
    0.06
     waive
    0.06
    escaped
    0.06
     Planning
    0.06
     Traffic
    0.06
    мат
    0.06
     сай
    0.06
     minib
    0.06
    traffic
    0.06
    Act Density 0.004%

    No Known Activations