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

    Neuronpedia

    INDEX
    Explanations

    code/web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rosse
    -0.06
     deleting
    -0.06
     dance
    -0.06
     china
    -0.06
     routers
    -0.06
    신청
    -0.06
     deported
    -0.05
    afb
    -0.05
    тра
    -0.05
    抱
    -0.05
    POSITIVE LOGITS
     Thời
    0.07
    การท
    0.07
     unins
    0.06
     Erick
    0.06
    ligt
    0.06
     форма
    0.06
     Od
    0.06
     Merchant
    0.06
    ễ
    0.06
    bands
    0.06
    Act Density 0.000%

    No Known Activations