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

    Neuronpedia

    INDEX
    Explanations

    Organized groups activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хоч
    -0.07
    Rent
    -0.06
     ง
    -0.06
     triples
    -0.06
    Started
    -0.06
    riter
    -0.06
    elper
    -0.06
     pře
    -0.06
     discrepancies
    -0.06
     soothing
    -0.06
    POSITIVE LOGITS
     Suggestions
    0.06
     visualize
    0.06
     juegos
    0.06
    ütün
    0.06
     societies
    0.06
    Thus
    0.06
     Rules
    0.06
     مرد
    0.06
     degrees
    0.06
     vaguely
    0.06
    Act Density 0.110%

    No Known Activations