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

    Neuronpedia

    INDEX
    Explanations

    draggable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    劳累
    -0.07
    MI
    -0.07
     penc
    -0.07
     Wander
    -0.07
    Contents
    -0.07
    Locations
    -0.07
    六大
    -0.07
     stumbled
    -0.07
     caption
    -0.07
    ultip
    -0.07
    POSITIVE LOGITS
    骑
    0.07
    ITableView
    0.07
     Desktop
    0.07
    ⊦
    0.06
     cray
    0.06
     cif
    0.06
    酵
    0.06
     zoo
    0.06
    доров
    0.06
    --[
    0.06
    Act Density 0.001%

    No Known Activations