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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igrants
    -0.07
    arg
    -0.07
    बर
    -0.06
    avl
    -0.06
    plug
    -0.06
    кому
    -0.06
    لیل
    -0.06
    ليات
    -0.06
    agg
    -0.06
    _corr
    -0.06
    POSITIVE LOGITS
    (mode
    0.07
    UDIO
    0.07
     Львів
    0.07
     pharm
    0.06
     basics
    0.06
    ;',↵
    0.06
    _archive
    0.06
     вариан
    0.06
     listings
    0.06
     leisure
    0.06
    Act Density 0.014%

    No Known Activations