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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     помогает
    -0.09
     石
    -0.08
    IEW
    -0.07
     Thus
    -0.07
    同步
    -0.07
    伍
    -0.07
    _STATS
    -0.07
    北京
    -0.07
     بپ
    -0.06
     mücadel
    -0.06
    POSITIVE LOGITS
     do
    0.10
    Dar
    0.07
     doing
    0.07
     thing
    0.07
    _DO
    0.07
     does
    0.06
    DO
    0.06
     DO
    0.06
    	do
    0.06
    .sqlite
    0.06
    Act Density 0.037%

    No Known Activations