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

    Neuronpedia

    INDEX
    Explanations

    become

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tranquille
    -0.08
     principios
    -0.08
     qualify
    -0.08
     situazione
    -0.08
    mentation
    -0.08
    东方
    -0.08
    情况
    -0.07
     rectangles
    -0.07
     persoane
    -0.07
     situatie
    -0.07
    POSITIVE LOGITS
     pivotal
    0.14
     invaluable
    0.11
     cornerstone
    0.11
    重要
    0.10
     મહત્વ
    0.10
     важ
    0.10
     crucial
    0.10
     Bestandteil
    0.10
     valuable
    0.10
     wichtiger
    0.10
    Act Density 0.078%

    No Known Activations