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

    Neuronpedia

    INDEX
    Explanations

    xml tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    堷
    0.43
     একখানি
    0.41
     স্বাদ
    0.40
    anglement
    0.38
     Pflege
    0.38
    PackageManager
    0.38
     forKey
    0.37
    SubDirectoryPath
    0.37
     brittle
    0.37
    ∂
    0.37
    POSITIVE LOGITS
    5
    0.41
    7
    0.41
          
    0.40
     completely
    0.39
    وك
    0.39
     immersive
    0.39
    von
    0.38
    0.38
     Fed
    0.38
            
    0.36
    Act Density 0.001%

    No Known Activations