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

    Neuronpedia

    INDEX
    Explanations

    code blocks and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supprimer
    0.27
    ঘ্রই
    0.24
    ",[],"
    0.24
    ൨
    0.23
     tasarım
    0.22
    ientôt
    0.22
    ྰ
    0.22
    쯜
    0.22
     titleImageUrl
    0.22
     إنشاء
    0.21
    POSITIVE LOGITS
      
    0.25
    …
    0.21
     e
    0.18
    s
    0.18
    ↵
    0.18
     pot
    0.18
     ion
    0.18
       
    0.17
     h
    0.17
     salt
    0.17
    Act Density 0.698%

    No Known Activations