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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    도별
    -0.07
    .team
    -0.06
     Newcastle
    -0.06
     döneminde
    -0.06
     deadliest
    -0.06
    (Debug
    -0.06
     dando
    -0.06
     tamil
    -0.06
     dolaş
    -0.06
     bride
    -0.06
    POSITIVE LOGITS
     Integr
    0.06
     нас
    0.06
    部门
    0.06
    ль
    0.06
     낮
    0.06
     واقع
    0.06
    eldon
    0.06
    	loc
    0.06
    etes
    0.06
    04
    0.06
    Act Density 0.013%

    No Known Activations