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

    Neuronpedia

    INDEX
    Explanations

    unaware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	md
    -0.06
     ivory
    -0.06
    shr
    -0.06
    $f
    -0.06
    oped
    -0.06
    (cm
    -0.06
     ;)↵↵
    -0.06
    伏
    -0.06
    Mas
    -0.06
    ahi
    -0.06
    POSITIVE LOGITS
    �
    0.06
    ellery
    0.06
    告
    0.06
     오
    0.06
    Creation
    0.06
     Airlines
    0.06
    包括
    0.06
     Zambia
    0.06
    talk
    0.06
     تلفن
    0.06
    Act Density 0.052%

    No Known Activations