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

    Neuronpedia

    INDEX
    Explanations

    diluted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Font
    -0.07
    кур
    -0.07
    QUIRES
    -0.06
    ﺘ
    -0.06
     canon
    -0.06
    _True
    -0.06
    нання
    -0.06
    �
    -0.06
    .transactions
    -0.06
     await
    -0.06
    POSITIVE LOGITS
    elements
    0.07
    Ｋ
    0.07
     masturb
    0.06
     вироб
    0.06
     quảng
    0.06
    (iParam
    0.06
    WHO
    0.06
    引用频次
    0.06
    مدة
    0.06
    редел
    0.06
    Act Density 0.001%

    No Known Activations