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

    Neuronpedia

    INDEX
    Explanations

    difference between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     normalised
    0.58
     YouTuber
    0.54
    Youtube
    0.54
     YouTube
    0.53
     YouT
    0.53
     vegan
    0.51
     youtube
    0.50
    ai
    0.49
    YouTube
    0.48
    ivre
    0.47
    POSITIVE LOGITS
     Hartford
    1.65
     Connecticut
    1.62
    ovll
    1.60
     gax
    1.59
     Buckeye
    1.58
    dated
    1.58
     RID
    1.55
     Ellington
    1.53
     Clk
    1.52
     Ariz
    1.51
    Act Density 0.241%

    No Known Activations