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

    Neuronpedia

    INDEX
    Explanations

    research databases and organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Exp
    -0.09
     ").
    -0.08
    小吃
    -0.08
    抱
    -0.08
    Outer
    -0.07
    프로그
    -0.07
    ㎎
    -0.07
    Cod
    -0.07
    """),↵
    -0.07
    产业结构
    -0.07
    POSITIVE LOGITS
     Johnson
    0.07
    .health
    0.07
    ▦
    0.07
     stesso
    0.07
    sembled
    0.07
    rikes
    0.07
    的時候
    0.07
    直播间
    0.07
     indiscrim
    0.07
    调配
    0.07
    Act Density 0.026%

    No Known Activations