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

    Neuronpedia

    INDEX
    Explanations

    mathematical solutions and equilibrium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (":/
    -0.07
    Ram
    -0.06
     Wishlist
    -0.06
    oved
    -0.06
    แผน
    -0.06
    ैल
    -0.06
     Patri
    -0.06
    рем
    -0.06
    ug
    -0.06
     Greek
    -0.06
    POSITIVE LOGITS
    /non
    0.07
     fucked
    0.07
    無料
    0.07
     stitches
    0.07
    /write
    0.06
    =m
    0.06
     дог
    0.06
    -working
    0.06
    shortcut
    0.06
    -&
    0.06
    Act Density 0.008%

    No Known Activations