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

    Neuronpedia

    INDEX
    Explanations

    changing naturally or balancing power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iconic
    0.47
     onboarding
    0.46
     headwinds
    0.46
     series
    0.45
     bartender
    0.45
     matchups
    0.45
     onstage
    0.45
    アイテム
    0.44
    となる
    0.44
     mesmerizing
    0.44
    POSITIVE LOGITS
    었어요
    0.46
    被害
    0.45
    🏡
    0.42
     neighbours
    0.41
     피해
    0.41
     ಮನೆ
    0.41
     Drainage
    0.39
     vivienda
    0.39
    سبب
    0.38
     korban
    0.38
    Act Density 0.002%

    No Known Activations