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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     služby
    -0.06
     Owens
    -0.06
     самого
    -0.06
    -talk
    -0.06
    app
    -0.06
     negatively
    -0.06
    虑
    -0.06
     sopr
    -0.06
    cala
    -0.06
    热
    -0.06
    POSITIVE LOGITS
    (clicked
    0.06
    샵
    0.06
     waved
    0.06
     "../../../../
    0.06
    ='<?
    0.06
    ість
    0.06
    InputElement
    0.06
    :add
    0.06
     principio
    0.06
     点击
    0.06
    Act Density 0.198%

    No Known Activations