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

    Neuronpedia

    INDEX
    Explanations

    eyewitness accounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seront
    -0.07
    .opensource
    -0.07
     указ
    -0.07
    武
    -0.06
     Tennis
    -0.06
    ♥
    -0.06
     phủ
    -0.06
     recurs
    -0.06
     systemic
    -0.06
     sách
    -0.06
    POSITIVE LOGITS
    규
    0.07
    ..........
    0.07
    \Validation
    0.06
     foul
    0.06
    ��
    0.06
     tranny
    0.06
    Rgb
    0.06
    .VERTICAL
    0.06
    chluss
    0.06
     swearing
    0.06
    Act Density 0.019%

    No Known Activations