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

    Neuronpedia

    INDEX
    Explanations

    lists of links and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Microsoft
    0.48
     AWS
    0.48
     Google
    0.47
     IBM
    0.46
     Amazon
    0.44
     Walmart
    0.43
     NVIDIA
    0.43
     Azure
    0.43
     OpenAI
    0.42
     Python
    0.42
    POSITIVE LOGITS
     ہمیں
    0.34
    素质
    0.32
     sebesar
    0.32
     justifica
    0.32
    nrow
    0.32
    解读
    0.31
    丝毫
    0.31
    ကြောင့်
    0.30
    Begriff
    0.30
    歯
    0.30
    Act Density 0.009%

    No Known Activations