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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buzz
    -0.07
     sensual
    -0.07
    	Button
    -0.07
    拓宽
    -0.07
    .icons
    -0.07
    春节
    -0.07
    神州
    -0.07
     ears
    -0.07
    Ion
    -0.07
     Vertex
    -0.07
    POSITIVE LOGITS
    лага
    0.07
    �
    0.06
    физическ
    0.06
     datab
    0.06
    clf
    0.06
    Ө
    0.06
    克服
    0.06
    פרויק
    0.06
    犯
    0.06
    撄
    0.06
    Act Density 0.001%

    No Known Activations