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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icode
    -0.33
    =view
    -0.30
    RING
    -0.28
    头顶
    -0.26
    %X
    -0.26
    éĹ®ä»ĸ
    -0.26
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.26
    å½ĺ
    -0.25
     cush
    -0.24
    %x
    -0.23
    POSITIVE LOGITS
    HS
    0.31
    indr
    0.30
    æľĢåIJİä¸Ģ个
    0.28
    rat
    0.28
    å¹³éĿĻ
    0.27
    ắm
    0.26
    çĿģ
    0.25
     HS
    0.25
    ãĥ©ãĥ¼
    0.25
    FP
    0.24
    Act Density 0.004%

    No Known Activations