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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ........
    -0.08
     antibody
    -0.07
     diagnostic
    -0.07
    ることが
    -0.07
    אפליק
    -0.07
    -arrow
    -0.07
    -wheel
    -0.07
    すぎ
    -0.07
     effectively
    -0.07
    劲
    -0.07
    POSITIVE LOGITS
    פרופיל
    0.08
    雒
    0.08
    尺
    0.07
    שווי
    0.07
     harvesting
    0.07
    ﭪ
    0.07
    ဂ
    0.07
     Pixels
    0.07
     routing
    0.07
    DELAY
    0.07
    Act Density 0.000%

    No Known Activations