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

    Neuronpedia

    INDEX
    Explanations

    bound

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of highway or road direction segments—e.g. northbound, eastbound, southbound lanes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    etypes
    -0.06
     Join
    -0.06
     tents
    -0.06
     eos
    -0.06
    _exceptions
    -0.06
     Frog
    -0.06
     Julian
    -0.06
     Cabinets
    -0.06
     knives
    -0.06
     Latvia
    -0.06
    POSITIVE LOGITS
    .RequestMethod
    0.08
     приход
    0.07
     qued
    0.07
     позволя
    0.07
     बढ़
    0.06
     bev
    0.06
    0.06
     πλη
    0.06
     kilomet
    0.06
     πο
    0.06
    Act Density 0.005%

    No Known Activations