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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     talks
    -0.07
     так
    -0.07
     å
    -0.07
     ein
    -0.07
    鎮
    -0.06
    Sing
    -0.06
    ording
    -0.06
    alf
    -0.06
     veg
    -0.06
    .Line
    -0.06
    POSITIVE LOGITS
    自主研发
    0.08
     najbliż
    0.07
    욧
    0.07
    蒻
    0.07
     UIColor
    0.07
     деят
    0.07
    pool
    0.07
    MetaData
    0.07
    产物
    0.07
    솥
    0.07
    Act Density 0.087%

    No Known Activations