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

    Neuronpedia

    INDEX
    Explanations

    election timeframes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thought
    -0.07
     Application
    -0.07
    Think
    -0.06
    .Clock
    -0.06
     NRF
    -0.06
    Runnable
    -0.06
     Taj
    -0.06
    退出
    -0.06
    enties
    -0.06
     chỉnh
    -0.06
    POSITIVE LOGITS
     snaží
    0.08
    Щ
    0.07
    赵
    0.06
    aben
    0.06
    phan
    0.06
    }&
    0.06
    UILTIN
    0.06
    �
    0.06
    	read
    0.06
     فس
    0.06
    Act Density 0.011%

    No Known Activations