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

    Neuronpedia

    INDEX
    Explanations

    Boundary changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дом
    -0.07
    esthesia
    -0.06
    .net
    -0.06
     Spotlight
    -0.06
     Lia
    -0.06
    像
    -0.06
     cables
    -0.06
    elik
    -0.06
    -new
    -0.06
     रव
    -0.06
    POSITIVE LOGITS
     protester
    0.07
    ροφορ
    0.06
    earned
    0.06
     деятельности
    0.06
    (namespace
    0.06
     depend
    0.06
    .Pos
    0.06
     peri
    0.06
    floating
    0.06
    |/
    0.06
    Act Density 0.016%

    No Known Activations