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

    Neuronpedia

    INDEX
    Explanations

    leash

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of walking a dog (e.g. walk, walking, leash, dog).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    film
    -0.07
     oats
    -0.07
     Godzilla
    -0.07
     fingerprints
    -0.07
     destin
    -0.06
    iti
    -0.06
    ，则
    -0.06
     Bus
    -0.06
    ographical
    -0.06
    girl
    -0.06
    POSITIVE LOGITS
    (mapStateToProps
    0.07
     lưới
    0.06
    textInput
    0.06
     ใช
    0.06
    (priv
    0.06
     lô
    0.06
    ----↵↵
    0.06
     컴
    0.06
     ‏
    0.06
    امة
    0.06
    Act Density 0.010%

    No Known Activations