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

    Neuronpedia

    INDEX
    Explanations

    repository URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     refuer
    0.41
     stiffer
    0.41
    プロダ
    0.37
    改进
    0.37
     modification
    0.37
     थिए
    0.37
     soften
    0.37
    Pract
    0.36
     powerhouse
    0.36
    Kil
    0.35
    POSITIVE LOGITS
    url
    0.47
     url
    0.44
    URL
    0.44
     Burs
    0.43
     bromide
    0.42
     html
    0.40
    NewUrl
    0.39
     romances
    0.39
     Bourke
    0.39
     situate
    0.38
    Act Density 0.000%

    No Known Activations