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

    Neuronpedia

    INDEX
    Explanations

    McCain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𫄸
    -0.07
    삻
    -0.07
    commend
    -0.07
    ighbors
    -0.07
    nde
    -0.06
     bek
    -0.06
    Bound
    -0.06
     bef
    -0.06
    癖
    -0.06
     turb
    -0.06
    POSITIVE LOGITS
     McCain
    0.09
    끊
    0.07
    łącz
    0.07
     última
    0.07
    腳
    0.06
    引っ越し
    0.06
    自己的
    0.06
    收缩
    0.06
     thuận
    0.06
     pierws
    0.06
    Act Density 0.001%

    No Known Activations