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

    Neuronpedia

    INDEX
    Explanations

    dog treats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سي
    0.62
     Forestry
    0.55
     Native
    0.54
    م
    0.52
     Id
    0.52
     Dü
    0.50
     Loyalty
    0.49
    ı
    0.49
     Tow
    0.48
     forestry
    0.48
    POSITIVE LOGITS
    tfidf
    0.62
    avasena
    0.61
    ╁
    0.59
    ButtonClick
    0.58
    ง
    0.56
    ಮಾರ
    0.55
    avacan
    0.55
    メソッド
    0.55
    dfs
    0.54
    क्यू
    0.54
    Act Density 0.001%

    No Known Activations