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

    Neuronpedia

    INDEX
    Explanations

    SQL table creation statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    влаж
    -0.07
     позволяет
    -0.07
    泰
    -0.07
     вокруг
    -0.07
     thiết
    -0.07
    灵动
    -0.07
     Comb
    -0.07
     Bugs
    -0.06
    ительно
    -0.06
    .examples
    -0.06
    POSITIVE LOGITS
     wages
    0.08
     loneliness
    0.07
     delays
    0.07
    לל
    0.07
    Audit
    0.07
    员工
    0.06
     Expansion
    0.06
    _week
    0.06
    islation
    0.06
    楼梯
    0.06
    Act Density 0.001%

    No Known Activations