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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MN
    -0.07
    mond
    -0.07
     extended
    -0.07
    NU
    -0.07
     Mon
    -0.07
    (MAX
    -0.07
    ook
    -0.07
     reactive
    -0.07
     Divide
    -0.07
    生动
    -0.06
    POSITIVE LOGITS
    Para
    0.06
     LOSS
    0.06
    _hpp
    0.06
     Чт
    0.06
    служ
    0.06
    interest
    0.06
    "net
    0.06
    뽄
    0.06
    防疫
    0.06
    âce
    0.06
    Act Density 0.051%

    No Known Activations