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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arium
    -0.08
    ration
    -0.07
    Uuid
    -0.07
    Repositories
    -0.07
    Middleware
    -0.07
    _reader
    -0.06
    之所以
    -0.06
    의
    -0.06
    🔽
    -0.06
    cff
    -0.06
    POSITIVE LOGITS
     власти
    0.07
    }',
    0.07
     Governor
    0.07
    话说
    0.07
    还没
    0.07
     teammate
    0.07
    ToList
    0.06
    	host
    0.06
     earners
    0.06
    订单
    0.06
    Act Density 0.002%

    No Known Activations