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

    Neuronpedia

    INDEX
    Explanations

    calculations and estimations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FAMILY
    -0.07
    	xml
    -0.07
     harvest
    -0.07
     Chains
    -0.07
     sponsors
    -0.06
     المنا
    -0.06
     Roof
    -0.06
     Domestic
    -0.06
     },↵↵↵
    -0.06
     camar
    -0.06
    POSITIVE LOGITS
     ['./
    0.07
     results
    0.07
    )["
    0.07
    都喜欢
    0.07
    𫖳
    0.07
    播
    0.07
    ffen
    0.07
    验证码
    0.06
    ulis
    0.06
    쁨
    0.06
    Act Density 0.092%

    No Known Activations