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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    综合整治
    -0.08
     leve
    -0.08
    激励
    -0.07
    芜
    -0.07
    ᴈ
    -0.07
    nu
    -0.07
    .quit
    -0.07
     resett
    -0.07
    !!!!!
    -0.07
     seper
    -0.07
    POSITIVE LOGITS
    脚步
    0.07
     Bread
    0.07
    discover
    0.07
    agen
    0.06
     Adult
    0.06
     beds
    0.06
    أخبار
    0.06
     sect
    0.06
     mornings
    0.06
    餐桌
    0.06
    Act Density 0.011%

    No Known Activations