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

    Neuronpedia

    INDEX
    Explanations

    physical characteristics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sok
    -0.08
     Đ
    -0.07
     THIRD
    -0.06
    에
    -0.06
    ILLISE
    -0.06
     lĩnh
    -0.06
    _middle
    -0.06
    投入
    -0.06
    ')))
    -0.06
    utm
    -0.06
    POSITIVE LOGITS
     Ladies
    0.07
    \Post
    0.07
     Europeans
    0.07
    ientes
    0.07
    蚤
    0.07
     useStyles
    0.07
    饭菜
    0.07
     Greece
    0.07
    ay
    0.07
    DataAdapter
    0.07
    Act Density 0.029%

    No Known Activations