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

    Neuronpedia

    INDEX
    Explanations

    energy/force

    np_max-act · gemini-2.0-flash

    This neuron detects Spanish words containing accented characters (á, é, í, ó, ú).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    оре
    -0.07
    ак
    -0.06
    開始
    -0.06
    ниць
    -0.06
    .collider
    -0.06
     people
    -0.06
     incontro
    -0.06
     згад
    -0.06
     услов
    -0.06
     prostituerte
    -0.06
    POSITIVE LOGITS
    .cn
    0.07
    พระราช
    0.07
    httpClient
    0.06
    -ng
    0.06
    _bg
    0.06
    /big
    0.06
     cli
    0.06
    .ADMIN
    0.06
     pulver
    0.06
    Invoker
    0.06
    Act Density 0.025%

    No Known Activations