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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تمامی
    -0.07
    orWhere
    -0.07
     относят
    -0.07
     vidět
    -0.06
    EDIATE
    -0.06
    福利
    -0.06
    /google
    -0.06
    .preferences
    -0.06
    าบาล
    -0.06
     ته
    -0.06
    POSITIVE LOGITS
     선수
    0.07
     pair
    0.07
    hur
    0.07
     fixture
    0.07
    دة
    0.07
    Node
    0.07
     Waters
    0.06
    efd
    0.06
    (id
    0.06
    userInfo
    0.06
    Act Density 0.001%

    No Known Activations