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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اته
    -0.07
    EPROM
    -0.06
    ictures
    -0.06
     layui
    -0.06
     scratched
    -0.06
    身体
    -0.06
     引
    -0.06
    _policy
    -0.06
    ождение
    -0.06
    ROWN
    -0.06
    POSITIVE LOGITS
     imagined
    0.07
     fen
    0.06
     Sunday
    0.06
    executor
    0.06
    query
    0.06
     ECS
    0.06
     karşı
    0.06
    со
    0.06
     favourite
    0.06
    .targets
    0.06
    Act Density 0.001%

    No Known Activations