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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EventArgs
    -0.07
    败
    -0.06
    词
    -0.06
    �
    -0.06
     Thornton
    -0.06
     ké
    -0.06
    _Item
    -0.06
     imbalance
    -0.06
     örgüt
    -0.06
     EditorGUI
    -0.06
    POSITIVE LOGITS
     облас
    0.07
    .flag
    0.06
    cell
    0.06
     inclusion
    0.06
    continental
    0.06
     Autom
    0.06
     Vertical
    0.06
    Apellido
    0.06
     Laurent
    0.06
     possessions
    0.06
    Act Density 0.045%

    No Known Activations