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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĮĿ
    -0.27
    åľ°æĿ¿
    -0.27
    èĦĸ
    -0.26
    -mask
    -0.26
    æīĭåĬ¿
    -0.25
    lbrace
    -0.24
    次æķ°
    -0.24
    vara
    -0.24
    éĺħ读åħ¨æĸĩ
    -0.24
     mask
    -0.24
    POSITIVE LOGITS
    帮å¿Ļ
    0.28
     metic
    0.26
    .android
    0.26
     Rain
    0.25
    .eng
    0.25
    jing
    0.24
    ä¸į认è¯Ĩ
    0.24
    çIJĩ
    0.24
    éľĩ
    0.24
    è±IJ
    0.24
    Act Density 0.002%

    No Known Activations