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

    Neuronpedia

    INDEX
    Explanations

    union

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Holmes
    -0.07
     Loren
    -0.07
    (os
    -0.07
     mlx
    -0.07
     nephew
    -0.07
    ریز
    -0.07
     ffmpeg
    -0.07
     fullfile
    -0.06
     parsley
    -0.06
    ouncing
    -0.06
    POSITIVE LOGITS
     wages
    0.07
     Ü
    0.07
    σιεύ
    0.06
     subtle
    0.06
    FunctionFlags
    0.06
    Labor
    0.06
    vehicle
    0.06
    verify
    0.06
     возник
    0.06
    biên
    0.06
    Act Density 0.005%

    No Known Activations