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

    Neuronpedia

    INDEX
    Explanations

    Book summaries/reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乘
    -0.07
    筵
    -0.07
     seaborn
    -0.07
     believe
    -0.07
    John
    -0.07
    .repaint
    -0.07
    เช
    -0.06
    拜
    -0.06
    缎
    -0.06
    隋
    -0.06
    POSITIVE LOGITS
     origins
    0.08
     beginnings
    0.07
    }{$
    0.07
    customerId
    0.07
     היהודי
    0.07
     JOB
    0.07
     культуры
    0.07
    个多
    0.07
     goal
    0.07
    很快就
    0.07
    Act Density 0.067%

    No Known Activations