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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash

    The neuron activates on Russian first-person plural references (forms of “we” and “our”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Liberals
    -0.06
     Regression
    -0.06
     Rice
    -0.06
     ordered
    -0.06
     id
    -0.06
    /register
    -0.06
    cors
    -0.06
    _Result
    -0.06
     робот
    -0.05
    ene
    -0.05
    POSITIVE LOGITS
    tura
    0.08
     오늘
    0.07
     Much
    0.07
    刚才
    0.06
     çıktı
    0.06
     สาข
    0.06
    щей
    0.06
     Анд
    0.06
    част
    0.06
    於
    0.06
    Act Density 0.076%

    No Known Activations