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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pink
    -0.08
    围
    -0.07
    某个
    -0.07
    等多个
    -0.07
    ellow
    -0.07
     NavParams
    -0.07
    _DISPATCH
    -0.06
     around
    -0.06
    DivElement
    -0.06
     View
    -0.06
    POSITIVE LOGITS
     switching
    0.07
    还将
    0.07
    HI
    0.07
    更新
    0.07
     Fleming
    0.07
    親
    0.07
    ฦ
    0.07
     Continuing
    0.06
     bleiben
    0.06
    .execution
    0.06
    Act Density 0.002%

    No Known Activations