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

    Neuronpedia

    INDEX
    Explanations

    quiet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     since
    -0.37
    since
    -0.34
    æīĢ以æĪij们
    -0.33
    å²Ĥ
    -0.31
    ä½ķåĨµ
    -0.31
    ãģªãģĦãģ®ãģ§
    -0.30
    ãģªãģĦãģ¨
    -0.30
    æĹ¢çĦ¶
    -0.30
    åĽłä¸ºæĪij们
    -0.29
    æ¯ķç«Ł
    -0.29
    POSITIVE LOGITS
    MARK
    0.26
    å°ıå¿ĥ
    0.25
    请æĤ¨
    0.25
    marked
    0.25
    缸è§ģ
    0.24
    .ba
    0.24
    å¤ļä½ĻçļĦ
    0.23
     mark
    0.23
     anybody
    0.23
    lowest
    0.23
    Act Density 0.009%

    No Known Activations