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

    Neuronpedia

    INDEX
    Explanations

    Surveillance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intended
    -0.07
     announcing
    -0.07
     appropriately
    -0.06
     opening
    -0.06
     notice
    -0.06
     Menu
    -0.06
    attery
    -0.06
    Unless
    -0.06
    حيح
    -0.06
     latest
    -0.06
    POSITIVE LOGITS
    varchar
    0.07
     Haskell
    0.06
    َي
    0.06
    حص
    0.06
     většinou
    0.06
    xon
    0.06
     tối
    0.06
     sog
    0.06
     почти
    0.06
    .'</
    0.06
    Act Density 0.031%

    No Known Activations