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

    Neuronpedia

    INDEX
    Explanations

    News/Official statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Perry
    -0.07
     Ger
    -0.07
     Aid
    -0.06
    582
    -0.06
    Russia
    -0.06
    navigator
    -0.06
     Ward
    -0.06
    (argc
    -0.05
     Hatch
    -0.05
     Brace
    -0.05
    POSITIVE LOGITS
     Рез
    0.07
     диамет
    0.07
    そして
    0.07
     日期
    0.07
     independents
    0.07
     connection
    0.07
    ां
    0.07
     vibrant
    0.07
     patio
    0.07
    ोत
    0.06
    Act Density 0.082%

    No Known Activations