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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кру
    -0.08
    ことです
    -0.07
    铢
    -0.07
    ROS
    -0.07
     AssemblyCompany
    -0.07
    四项
    -0.07
    🏋
    -0.07
    ⤝
    -0.07
    ✸
    -0.06
    础
    -0.06
    POSITIVE LOGITS
     Deer
    0.07
     Made
    0.07
    جل
    0.07
    Liter
    0.07
     Lid
    0.07
     Upper
    0.06
    inte
    0.06
    _Per
    0.06
    	inter
    0.06
     Tir
    0.06
    Act Density 0.010%

    No Known Activations