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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    승
    -0.07
    Thr
    -0.07
     chàng
    -0.06
     hạnh
    -0.06
    双赢
    -0.06
     Tucker
    -0.06
    切
    -0.06
     injust
    -0.06
     du
    -0.06
     rừng
    -0.06
    POSITIVE LOGITS
    -color
    0.07
    .Low
    0.07
    	Code
    0.07
     enclosed
    0.07
    gages
    0.07
     strtol
    0.06
    (inputs
    0.06
    教堂
    0.06
    注视
    0.06
    人力
    0.06
    Act Density 0.002%

    No Known Activations