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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    州市
    -0.07
     ISSUE
    -0.06
     oro
    -0.06
    .fname
    -0.06
    _ft
    -0.06
    获得了
    -0.06
     cigarettes
    -0.06
    WG
    -0.06
     السودان
    -0.06
    郭
    -0.06
    POSITIVE LOGITS
    /team
    0.07
     نهاية
    0.07
    за
    0.07
    复活
    0.07
     TOO
    0.07
     stay
    0.07
    diğinde
    0.07
    抬
    0.06
    _dual
    0.06
    �
    0.06
    Act Density 0.184%

    No Known Activations