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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /log
    -0.07
    ehicle
    -0.07
    ative
    -0.07
     ny
    -0.06
     geometry
    -0.06
     Doll
    -0.06
     studied
    -0.06
     Craw
    -0.06
    ystal
    -0.06
    VectorXd
    -0.06
    POSITIVE LOGITS
     работу
    0.07
    FILTER
    0.06
    0.06
     مورد
    0.06
     Gtk
    0.06
    érer
    0.06
     bitir
    0.06
     oluşan
    0.06
     підс
    0.06
     nhé
    0.06
    Act Density 0.008%

    No Known Activations