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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hentet
    -0.65
    +#+#
    -0.65
     magasiner
    -0.64
    WebServlet
    -0.63
    kloped
    -0.62
     ujednoznacz
    -0.60
    gameserver
    -0.59
     Administrativna
    -0.57
    Personendaten
    -0.56
    RegressionTest
    -0.54
    POSITIVE LOGITS
    setPointSize
    0.58
     समीक्षक
    0.58
     organ
    0.56
     organs
    0.52
    cloak
    0.52
     RequestMethod
    0.52
     sections
    0.52
     staffs
    0.51
     hawks
    0.51
     daarvoor
    0.50
    Act Density 0.001%

    No Known Activations