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

    Neuronpedia

    INDEX
    Explanations

    apollo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Json
    -0.08
     Tree
    -0.08
    草莓
    -0.08
     >=
    -0.07
    _dev
    -0.07
    uble
    -0.07
    .Tree
    -0.07
     Twitch
    -0.07
    状态
    -0.07
     Grab
    -0.07
    POSITIVE LOGITS
    bolt
    0.08
     Signals
    0.07
    我希望
    0.07
    uais
    0.07
    毫无疑问
    0.07
    ��이지
    0.07
    政务
    0.07
     quiero
    0.07
     llegó
    0.07
     POR
    0.07
    Act Density 0.002%

    No Known Activations