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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å¼Ģæľº
    -0.29
    å¾Īé«ĺçļĦ
    -0.29
    é«ĺçļĦ
    -0.28
    å¾Īä½İ
    -0.28
    é«ĺæĺĤ
    -0.27
    åĩºè¡Ģ
    -0.26
    Nx
    -0.25
    studio
    -0.24
    æľĢé«ĺçļĦ
    -0.24
     microsoft
    -0.24
    POSITIVE LOGITS
    ass
    0.25
    rita
    0.25
     Hopkins
    0.25
    asses
    0.25
     Importance
    0.24
    uded
    0.24
    京津
    0.24
    edis
    0.24
     CommandType
    0.24
     Comments
    0.23
    Act Density 0.002%

    No Known Activations