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

    Neuronpedia

    INDEX
    Explanations

    android bundle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ary
    0.41
     revolution
    0.38
     constructions
    0.38
     harsh
    0.38
     forecasting
    0.37
    super
    0.37
    sequences
    0.37
    ulously
    0.37
     Forecasting
    0.36
    mixing
    0.36
    POSITIVE LOGITS
     ディ
    0.63
     Андроид
    0.57
    יר
    0.55
    ウィンドウ
    0.55
    トップ
    0.54
     ร้าน
    0.53
     Ziele
    0.52
     タイ
    0.51
     Фон
    0.50
     言っ
    0.50
    Act Density 0.000%

    No Known Activations