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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    行政部门
    -0.08
    	auth
    -0.07
     Św
    -0.07
    ܣ
    -0.07
    ī
    -0.07
     read
    -0.06
    	yy
    -0.06
    -info
    -0.06
     biochemical
    -0.06
    -FIRST
    -0.06
    POSITIVE LOGITS
    [w
    0.08
    (new
    0.07
     eup
    0.07
    شاشة
    0.07
    给他们
    0.07
    دا
    0.07
     Herald
    0.07
    .Par
    0.07
     depress
    0.07
    十多
    0.06
    Act Density 0.107%

    No Known Activations