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

    Neuronpedia

    INDEX
    Explanations

    Accommodation occupancy and sleeping arrangements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noticing
    -0.07
    Primary
    -0.07
    .Storage
    -0.07
    一层
    -0.07
    看着
    -0.07
     chees
    -0.07
    Simon
    -0.07
    吃了
    -0.07
     Oktober
    -0.07
    .mc
    -0.07
    POSITIVE LOGITS
     lleg
    0.06
    RM
    0.06
    总结
    0.06
    .Diagnostics
    0.06
    🏝
    0.06
    我当时
    0.06
    ɽ
    0.06
    껨
    0.06
    �
    0.06
    㥄
    0.06
    Act Density 0.011%

    No Known Activations