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

    Neuronpedia

    INDEX
    Explanations

    weather conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plot
    0.38
    ポリシー
    0.38
    تمع
    0.38
     デ
    0.38
     एव
    0.37
    思想
    0.37
    トレ
    0.36
     ベース
    0.36
     マル
    0.36
     sooner
    0.35
    POSITIVE LOGITS
     playfully
    0.43
     fertilisers
    0.38
     cheeky
    0.38
    nament
    0.38
    Há
    0.38
     Gere
    0.37
    </footer>
    0.37
     यश
    0.37
     favours
    0.37
     Sheeran
    0.37
    Act Density 0.001%

    No Known Activations