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

    Neuronpedia

    INDEX
    Explanations

    items categorized for clarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    赖
    0.39
    鍏
    0.39
    సిన
    0.38
    仗
    0.38
     dokładnie
    0.37
    تاة
    0.36
    കുന്ന
    0.35
    DesignTime
    0.35
     pisan
    0.34
    idelity
    0.34
    POSITIVE LOGITS
     categor
    3.23
     categorize
    3.22
     categorization
    3.22
     categorized
    3.11
    categor
    2.98
     Categor
    2.86
    分类
    2.80
     categories
    2.77
    Categor
    2.77
     kategor
    2.72
    Act Density 0.536%

    No Known Activations