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

    Neuronpedia

    INDEX
    Explanations

    returning home

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens involved in “to [destination]” phrases indicating movement or return to a place.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    นด
    -0.06
    함
    -0.06
    quete
    -0.06
     seinem
    -0.06
    Launch
    -0.06
    щие
    -0.06
     レ
    -0.06
    channel
    -0.06
    ительного
    -0.06
    kke
    -0.06
    POSITIVE LOGITS
    urved
    0.06
    ick
    0.06
    ポイント
    0.06
     boto
    0.06
     recognize
    0.06
    (Config
    0.06
     Popular
    0.06
     HTTP
    0.06
     :↵↵↵↵
    0.06
    _VOID
    0.06
    Act Density 0.019%

    No Known Activations