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

    Neuronpedia

    INDEX
    Explanations

    old

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä½ķåĨµ
    -0.28
    oled
    -0.27
    èµĤ
    -0.26
    umber
    -0.26
    å®ŀå¹²
    -0.25
     táºŃn
    -0.25
    ainen
    -0.25
    łģ
    -0.24
    arine
    -0.24
    Allocator
    -0.24
    POSITIVE LOGITS
     consort
    0.28
    анÑģ
    0.26
    DEN
    0.25
    æĹłéĻIJ
    0.25
    æķ´é¡¿
    0.25
     inflict
    0.24
    çŃĴ
    0.24
    ç»ĵå©ļ
    0.24
     testify
    0.23
    пи
    0.23
    Act Density 0.002%

    No Known Activations