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

    Neuronpedia

    INDEX
    Explanations

    scientific research, health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dess
    -0.06
    只有
    -0.06
     sucked
    -0.06
    ไร
    -0.06
    唯
    -0.06
    .want
    -0.06
     vẫn
    -0.06
    ียก
    -0.06
    _or
    -0.06
     bugs
    -0.06
    POSITIVE LOGITS
     природ
    0.08
     ()
↵
    0.07
    工業
    0.07
    peč
    0.06
    (pat
    0.06
    (course
    0.06
    _soc
    0.06
     家
    0.06
     deque
    0.06
     世
    0.06
    Act Density 0.204%

    No Known Activations