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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setWidth
    -0.07
     participating
    -0.07
    otland
    -0.07
     erected
    -0.07
    四个意识
    -0.07
    (Html
    -0.06
    降雨
    -0.06
    .Transactional
    -0.06
    ös
    -0.06
     donating
    -0.06
    POSITIVE LOGITS
    abi
    0.08
     quân
    0.07
    畜
    0.07
    —that
    0.07
    sequential
    0.06
     לעולם
    0.06
     clang
    0.06
    ﰘ
    0.06
    储量
    0.06
    Mean
    0.06
    Act Density 0.008%

    No Known Activations