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

    Neuronpedia

    INDEX
    Explanations

    Technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Addr
    -0.07
    都
    -0.07
    .HORIZONTAL
    -0.07
     Eleven
    -0.07
    沙漠
    -0.07
    зв
    -0.06
    끙
    -0.06
    툭
    -0.06
    꿕
    -0.06
    簝
    -0.06
    POSITIVE LOGITS
    	job
    0.07
    ân
    0.07
    _pr
    0.07
    #[
    0.07
    通行
    0.07
     inmates
    0.07
    연
    0.07
    arak
    0.06
    王某
    0.06
    	rs
    0.06
    Act Density 0.032%

    No Known Activations