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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deb
    -0.07
    (Response
    -0.07
    uning
    -0.07
    [loc
    -0.07
    죔
    -0.07
    _desc
    -0.07
     GP
    -0.07
    _Desc
    -0.07
    "A
    -0.07
    的有效
    -0.07
    POSITIVE LOGITS
    液体
    0.08
    린
    0.07
    .ur
    0.07
     aquarium
    0.07
    🚜
    0.07
     stre
    0.07
     tyre
    0.07
    蛳
    0.06
    火车
    0.06
    🐻
    0.06
    Act Density 0.004%

    No Known Activations