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

    Neuronpedia

    INDEX
    Explanations

    text processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ALL
    -0.07
     mars
    -0.07
    ItemList
    -0.07
     Sell
    -0.06
     chats
    -0.06
     stochastic
    -0.06
    	scroll
    -0.06
    LEVEL
    -0.06
     DatabaseReference
    -0.06
    /actions
    -0.06
    POSITIVE LOGITS
     결혼
    0.07
    (inode
    0.07
    _blog
    0.07
    菌
    0.07
    collector
    0.07
     toh
    0.06
     dreadful
    0.06
    rej
    0.06
    ンバ
    0.06
     ig
    0.06
    Act Density 0.022%

    No Known Activations