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

    Neuronpedia

    INDEX
    Explanations

    timestamp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缴费
    -0.08
    .context
    -0.07
    꼍
    -0.07
    看不到
    -0.06
    status
    -0.06
    (device
    -0.06
     فهو
    -0.06
    (Element
    -0.06
    간
    -0.06
     copyright
    -0.06
    POSITIVE LOGITS
    "}
    0.07
    睁
    0.07
     wound
    0.07
    team
    0.06
     Loud
    0.06
    loys
    0.06
     ""}↵
    0.06
    改变了
    0.06
    .loc
    0.06
    },{"
    0.06
    Act Density 0.002%

    No Known Activations