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

    Neuronpedia

    INDEX
    Explanations

    Light transmission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    了解到
    -0.07
     questa
    -0.07
     Ко
    -0.06
     LOGGER
    -0.06
     będzie
    -0.06
     Mag
    -0.06
    kład
    -0.06
    萧
    -0.06
    PS
    -0.06
     Darling
    -0.06
    POSITIVE LOGITS
     Jews
    0.08
    羿
    0.07
    重返
    0.07
     =======
    0.07
     starts
    0.07
    ﹽ
    0.07
    打断
    0.07
    开启了
    0.07
    烘焙
    0.07
    猷
    0.07
    Act Density 0.044%

    No Known Activations