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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    偿
    -0.08
     camper
    -0.08
    -ir
    -0.08
     réduire
    -0.08
     развлеч
    -0.08
    ir
    -0.08
     résist
    -0.08
    -payment
    -0.08
     ир
    -0.08
     escritura
    -0.08
    POSITIVE LOGITS
     Lorem
    0.09
     Huawei
    0.09
     IEEE
    0.09
     Zhou
    0.08
     北京
    0.08
                                                ↵
    0.08
     elaborado
    0.08
    Industrial
    0.08
     kuo
    0.08
     Jing
    0.07
    Act Density 0.008%

    No Known Activations