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

    Neuronpedia

    INDEX
    Explanations

    assign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Encoder
    -0.07
     recht
    -0.07
    Ads
    -0.07
    irteen
    -0.07
    313
    -0.06
    Produ
    -0.06
    Category
    -0.06
    ipples
    -0.06
    ıldığında
    -0.06
    iversary
    -0.06
    POSITIVE LOGITS
    (',');↵
    0.07
     {};
↵
    0.06
     국내
    0.06
    .");
↵
    0.06
     FB
    0.06
    ↵      ↵
    0.06
     手机
    0.06
    .selectAll
    0.06
     Legislature
    0.06
    ForObject
    0.06
    Act Density 0.015%

    No Known Activations