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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rubbing
    0.44
     stup
    0.44
     messa
    0.42
     backwards
    0.42
     clever
    0.42
     መል
    0.42
    戤
    0.42
     Ré
    0.42
     Yeshu
    0.42
     답
    0.41
    POSITIVE LOGITS
    ีก
    0.40
    ➧
    0.38
    スポーツ
    0.37
    和你
    0.37
    casino
    0.37
    JL
    0.36
    STORAGE
    0.36
    WL
    0.36
    CHAPTER
    0.36
    льными
    0.36
    Act Density 0.001%

    No Known Activations