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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suf
    -0.06
     akan
    -0.06
     LOT
    -0.06
    atra
    -0.06
     deadlock
    -0.06
     burada
    -0.06
    чини
    -0.06
     Loft
    -0.06
    +"]
    -0.06
     russian
    -0.06
    POSITIVE LOGITS
     gettimeofday
    0.07
    "/
    0.07
    :"-
    0.07
    ='/
    0.06
    ementia
    0.06
    	try
    0.06
    优秀
    0.06
    xdc
    0.06
    @"
    0.06
    =============↵
    0.06
    Act Density 0.000%

    No Known Activations