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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зміни
    -0.06
     mot
    -0.06
    ۴۰
    -0.06
     krist
    -0.06
    รอบ
    -0.06
    prefix
    -0.06
     �
    -0.06
     صفحه
    -0.06
     oslo
    -0.06
     Optimization
    -0.06
    POSITIVE LOGITS
    �
    0.06
     Mixing
    0.06
     khỏe
    0.06
     Stam
    0.06
     ging
    0.06
    elijke
    0.06
     بأن
    0.06
     полез
    0.06
     Wass
    0.06
     Tencent
    0.06
    Act Density 0.082%

    No Known Activations