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

    Neuronpedia

    INDEX
    Explanations

    Code/Markup/Non-English Text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ql
    -0.06
     parasites
    -0.06
     far
    -0.06
     करव
    -0.06
     physics
    -0.06
    500
    -0.06
    校
    -0.06
     formerly
    -0.06
    icals
    -0.06
     pop
    -0.06
    POSITIVE LOGITS
    (Gtk
    0.09
    -->
↵
    0.07
     Spart
    0.07
    olem
    0.07
    有什么
    0.07
     ssize
    0.06
    diğini
    0.06
    讨
    0.06
    (Route
    0.06
    nutrition
    0.06
    Act Density 0.446%

    No Known Activations