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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mc
    -0.07
     professionals
    -0.06
     Cou
    -0.06
    _CASE
    -0.06
    官
    -0.06
    conde
    -0.06
    鬼
    -0.06
    ancel
    -0.06
    nal
    -0.06
    ной
    -0.06
    POSITIVE LOGITS
     имеет
    0.07
     effortlessly
    0.07
    (bundle
    0.06
    μένος
    0.06
     evolved
    0.06
     discrim
    0.06
    選択
    0.06
     Moran
    0.06
    (sequence
    0.06
    IMIZE
    0.06
    Act Density 0.068%

    No Known Activations