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

    Neuronpedia

    INDEX
    Explanations

    links to websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ∼
    0.65
    CGPoint
    0.64
     restructure
    0.61
     Lifestyle
    0.60
     cultural
    0.59
     Cultural
    0.58
     improve
    0.58
     Improve
    0.57
    వల
    0.57
    〜
    0.57
    POSITIVE LOGITS
     ซึ่ง
    1.02
     hvilket
    0.94
     என்றார்
    0.92
     으로
    0.90
     což
    0.89
     이라고
    0.88
     وهذا
    0.86
     vilket
    0.85
     지금까지
    0.84
     という
    0.84
    Act Density 0.250%

    No Known Activations