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

    Neuronpedia

    INDEX
    Explanations

    Chinese names and tech companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     one
    1.17
     her
    0.95
     on
    0.94
     given
    0.94
    ↵↵
    0.92
     budget
    0.91
     in
    0.89
     its
    0.89
     One
    0.80
     $\
    0.79
    POSITIVE LOGITS
    anchen
    2.39
    weixin
    2.35
    anyi
    2.30
     Xiang
    2.26
     Xue
    2.26
     Hao
    2.22
    Dao
    2.21
     Tencent
    2.20
    rui
    2.18
    <unused505>
    2.18
    Act Density 0.048%

    No Known Activations