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

    Neuronpedia

    INDEX
    Explanations

    Reader already knows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cleanup
    -0.07
    ustral
    -0.07
    中国移动
    -0.07
    owan
    -0.07
    ∖
    -0.07
     Everett
    -0.06
    _items
    -0.06
     surveyed
    -0.06
    CHAT
    -0.06
     currents
    -0.06
    POSITIVE LOGITS
    介绍说
    0.08
    (vp
    0.07
     العلم
    0.07
     праз
    0.07
    惟
    0.07
    IMIZE
    0.07
     сочета
    0.07
    就會
    0.07
    CppMethodInitialized
    0.07
     hyp
    0.06
    Act Density 0.129%

    No Known Activations