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

    Neuronpedia

    INDEX
    Explanations

    uniform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ativity
    -0.07
    noteq
    -0.07
     dealloc
    -0.07
     auctions
    -0.06
    ToStr
    -0.06
     требования
    -0.06
    thon
    -0.06
    scripts
    -0.06
    _asm
    -0.06
    讲
    -0.06
    POSITIVE LOGITS
    Drink
    0.06
     organized
    0.06
    рей
    0.06
    _about
    0.06
     drawings
    0.06
    .Inventory
    0.06
    /I
    0.06
    /search
    0.06
    0.06
     вод
    0.06
    Act Density 0.004%
    No Known Activations