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

    Neuronpedia

    INDEX
    Explanations

    extension identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رہنما
    0.42
     给
    0.41
     hóa
    0.41
     相关
    0.40
     сюжет
    0.39
     أن
    0.39
     aprend
    0.39
     personalidad
    0.39
     созда
    0.38
     помощь
    0.38
    POSITIVE LOGITS
    theoretical
    0.43
    比較的
    0.42
    limit
    0.42
    categorical
    0.41
    excluding
    0.41
    合計
    0.41
    total
    0.40
    single
    0.40
    excludes
    0.40
    tree
    0.39
    Act Density 0.001%

    No Known Activations