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

    Neuronpedia

    INDEX
    Explanations

    video platforms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    山区
    -0.11
    澳门
    -0.10
    香港
    -0.10
     mountainous
    -0.09
    ============
    -0.09
     пожар
    -0.09
     Ronald
    -0.09
     montagne
    -0.09
    доров
    -0.09
    دخل
    -0.09
    POSITIVE LOGITS
    上的
    0.10
    Auth
    0.08
    -based
    0.07
    CI
    0.07
     classifiers
    0.07
    Format
    0.07
    apple
    0.07
     or
    0.06
     creators
    0.06
    上一
    0.06
    Act Density 0.075%

    No Known Activations