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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فال
    -0.07
    \Route
    -0.07
     скор
    -0.07
    籍
    -0.06
    .Char
    -0.06
    _winner
    -0.06
    Normals
    -0.06
     bookstore
    -0.06
     лок
    -0.06
    _pick
    -0.06
    POSITIVE LOGITS
    pcf
    0.07
     Prote
    0.06
     tsp
    0.06
     grammar
    0.06
    és
    0.06
     žád
    0.06
    rrha
    0.06
    Th
    0.06
    prm
    0.06
     wishes
    0.06
    Act Density 0.001%

    No Known Activations