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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     permane
    -0.09
     बनाया
    -0.08
     बना
    -0.08
    GO
    -0.08
     distinto
    -0.08
    Movies
    -0.07
     continental
    -0.07
    -0.07
     definido
    -0.07
     destinado
    -0.07
    POSITIVE LOGITS
    询
    0.12
    咨询
    0.11
    詢
    0.11
     politely
    0.11
    看看
    0.10
     выяс
    0.10
    沟
    0.10
     inquire
    0.10
     문의
    0.10
     জানান
    0.10
    Act Density 0.087%
    No Known Activations