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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Г
    -0.07
    mlx
    -0.07
    Ч
    -0.06
     mlx
    -0.06
    患
    -0.06
    Im
    -0.06
     ä
    -0.06
    ap
    -0.06
     �
    -0.06
     가진
    -0.06
    POSITIVE LOGITS
    ified
    0.07
     Saskatchewan
    0.07
     colourful
    0.06
    视频
    0.06
     vibrating
    0.06
     Nous
    0.06
     Arizona
    0.06
    dens
    0.06
    _difference
    0.06
     omp
    0.06
    Act Density 0.002%

    No Known Activations