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

    Neuronpedia

    INDEX
    Explanations

    numbers and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Violet
    -0.08
     rap
    -0.08
     Terra
    -0.07
     recipients
    -0.07
    	alert
    -0.07
    350
    -0.07
     לנ
    -0.07
     Damit
    -0.07
     Jensen
    -0.07
    ึ้น
    -0.07
    POSITIVE LOGITS
    ，而
    0.10
     PERFORMANCE
    0.09
    Successful
    0.08
    Performance
    0.08
    transpose
    0.08
     Performance
    0.08
    -original
    0.08
    ，却
    0.08
    、本
    0.08
    を見る
    0.08
    Act Density 0.034%

    No Known Activations