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

    Neuronpedia

    INDEX
    Explanations

    paragraph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    侵害
    -0.07
    OME
    -0.07
    .Inv
    -0.07
     SUMMARY
    -0.07
    ｧ
    -0.06
    馕
    -0.06
    出击
    -0.06
    徽
    -0.06
     الذين
    -0.06
     الأول
    -0.06
    POSITIVE LOGITS
     plank
    0.08
     acos
    0.08
    *sp
    0.07
    	clock
    0.07
     esac
    0.07
    因为我们
    0.07
    眼界
    0.07
    =M
    0.07
     panels
    0.07
     panorama
    0.07
    Act Density 0.011%

    No Known Activations