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

    Neuronpedia

    INDEX
    Explanations

    increasingly relevant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ชอบ
    0.54
    が好き
    0.47
     좋아하는
    0.46
    addEdge
    0.46
    喜欢
    0.45
     любит
    0.45
    Ⲕ
    0.42
     люблю
    0.42
     সাধারণত
    0.42
     dipende
    0.41
    POSITIVE LOGITS
    显得
    0.81
     increasingly
    0.79
     더욱
    0.73
    格外
    0.69
     understandably
    0.65
     relevance
    0.64
     relev
    0.64
     inevitably
    0.64
     semakin
    0.64
     Increasingly
    0.64
    Act Density 0.006%

    No Known Activations