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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     These
    -0.07
    modification
    -0.06
     setInterval
    -0.06
    /add
    -0.06
    来看看
    -0.06
    次
    -0.06
    黎
    -0.06
     decided
    -0.06
    东南
    -0.06
    移
    -0.06
    POSITIVE LOGITS
     adap
    0.07
     antennas
    0.07
    (dst
    0.07
    庞大的
    0.07
    늄
    0.07
     metal
    0.07
    CAN
    0.06
     dataset
    0.06
     enamel
    0.06
     Hồ
    0.06
    Act Density 0.003%

    No Known Activations