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

    Neuronpedia

    INDEX
    Explanations

    Native American history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Having
    -0.08
     ruining
    -0.07
    vertime
    -0.07
    	num
    -0.07
     launcher
    -0.07
     maxim
    -0.07
    .txt
    -0.07
     youthful
    -0.07
     Commission
    -0.06
    piece
    -0.06
    POSITIVE LOGITS
    校长
    0.07
    彩虹
    0.06
    麈
    0.06
    ws
    0.06
    otted
    0.06
    扔
    0.06
     errorCode
    0.06
    als
    0.06
     단
    0.06
     nhị
    0.06
    Act Density 0.011%

    No Known Activations