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

    Neuronpedia

    INDEX
    Explanations

    sell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cook
    -0.07
    ，请
    -0.07
     enabling
    -0.07
    miss
    -0.06
     dissolved
    -0.06
    QUENCE
    -0.06
     West
    -0.06
     Dong
    -0.06
     Reference
    -0.06
    ulg
    -0.06
    POSITIVE LOGITS
    بشر
    0.07
    ynec
    0.07
    压抑
    0.07
    짊
    0.07
    狒
    0.07
     gamer
    0.07
    音箱
    0.07
    摇头
    0.07
    难受
    0.07
    不孕
    0.07
    Act Density 0.012%

    No Known Activations