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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    775
    -0.07
     док
    -0.07
     currentPage
    -0.06
    аними
    -0.06
    еними
    -0.06
    enity
    -0.06
    縮
    -0.06
     Країна
    -0.06
    。」
    -0.06
    Determin
    -0.06
    POSITIVE LOGITS
     helt
    0.07
    {}↵
    0.06
     mort
    0.06
    Ÿ
    0.06
    .inc
    0.06
     MIL
    0.06
     verdade
    0.06
     prejud
    0.06
     SELF
    0.06
    Boundary
    0.06
    Act Density 0.016%

    No Known Activations