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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cores
    -0.07
    edited
    -0.07
     Вот
    -0.07
    Bindable
    -0.06
     являются
    -0.06
     yu
    -0.06
     свою
    -0.06
     اث
    -0.06
     agg
    -0.06
     πέ
    -0.06
    POSITIVE LOGITS
     HashSet
    0.21
    HashSet
    0.11
    .HashSet
    0.08
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.07
     hooks
    0.06
    ベル
    0.06
     checking
    0.06
    uyordu
    0.06
    지노
    0.06
     vữ
    0.06
    Act Density 0.002%

    No Known Activations