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

    Neuronpedia

    INDEX
    Explanations

    abstract nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বাসীর
    0.42
    成功的
    0.38
    ichés
    0.37
    ೀಯ
    0.37
     ಆದರೆ
    0.35
    iores
    0.35
     unwelcome
    0.35
     facie
    0.35
     believers
    0.34
     Tweets
    0.34
    POSITIVE LOGITS
     use
    0.64
     practise
    0.54
     practice
    0.53
     availability
    0.52
     manufacture
    0.50
     role
    0.45
     sale
    0.45
     dominance
    0.44
     status
    0.43
     usage
    0.43
    Act Density 0.016%

    No Known Activations