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

    Neuronpedia

    INDEX
    Explanations

    Filepaths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thirsty
    -0.07
    夜
    -0.07
    configured
    -0.07
    displayText
    -0.06
     timed
    -0.06
    비
    -0.06
     ci
    -0.06
     Threshold
    -0.06
    监督
    -0.06
    desc
    -0.06
    POSITIVE LOGITS
     реги
    0.07
    (robot
    0.06
     Цент
    0.06
    」「
    0.06
     陳
    0.06
    (cluster
    0.06
    .dense
    0.06
     일반
    0.06
     краї
    0.06
    	pstmt
    0.06
    Act Density 0.003%

    No Known Activations