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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    郑
    -0.08
    实事求是
    -0.07
    ="↵
    -0.07
     multiprocessing
    -0.07
     güncel
    -0.07
     Palestinian
    -0.07
    Ptr
    -0.06
    全程
    -0.06
    prowadzi
    -0.06
     Disconnect
    -0.06
    POSITIVE LOGITS
    -law
    0.07
    atoire
    0.07
     aussi
    0.07
    structure
    0.07
    刀
    0.07
    baum
    0.06
     Law
    0.06
     manos
    0.06
    _flash
    0.06
    勘
    0.06
    Act Density 0.148%

    No Known Activations