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

    Neuronpedia

    INDEX
    Explanations

    General conversational English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,map
    -0.27
    hör
    -0.24
     Uncategorized
    -0.24
    ention
    -0.24
    “
    -0.24
    ,W
    -0.23
    oy
    -0.23
    d
    -0.23
    æľīä¸Ģå®ļ
    -0.23
    Ur
    -0.23
    POSITIVE LOGITS
    æĽ´æĺ¯
    1.07
     further
    0.80
    æĽ´è¦ģ
    0.80
     even
    0.75
    æĽ´
    0.75
    è¿Ľä¸ĢæŃ¥
    0.71
    æĽ´ä¸º
    0.71
    æĽ´åĬł
    0.70
    尤为
    0.67
    çĶļèĩ³
    0.66
    Act Density 0.005%

    No Known Activations