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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash

    products related to child safety and convenience in transportation.

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

    This neuron picks out the short navigational or heading tokens that introduce or separate product description sections (e.g. “Read,” “more,” “The,” “On,” and other boilerplate header words).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    에서도
    -0.07
    _statistics
    -0.06
    osomes
    -0.06
    Mos
    -0.06
     Mods
    -0.06
    LOC
    -0.06
    daemon
    -0.06
     Measurements
    -0.06
    .delegate
    -0.06
     Bios
    -0.06
    POSITIVE LOGITS
    \F
    0.07
    專
    0.07
    gregator
    0.06
    leşik
    0.06
     anyways
    0.06
    ีน
    0.06
    obuf
    0.06
    	card
    0.06
     ostatní
    0.06
     �
    0.06
    Act Density 0.038%

    No Known Activations