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

    Neuronpedia

    INDEX
    Explanations

    applications and registrations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (hostname
    -0.07
    圉
    -0.07
    יכון
    -0.06
    ⸮
    -0.06
    ioc
    -0.06
    .iOS
    -0.06
    服务区
    -0.06
     trust
    -0.06
    涣
    -0.06
     toda
    -0.06
    POSITIVE LOGITS
     찾아
    0.07
    --------↵
    0.07
    /design
    0.07
    (Context
    0.07
     Accent
    0.07
     chiff
    0.07
    AREN
    0.06
    cheng
    0.06
    .WriteByte
    0.06
    减肥
    0.06
    Act Density 0.028%

    No Known Activations