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

    Neuronpedia

    INDEX
    Explanations

    web-related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     культу
    -0.07
    nesty
    -0.06
     своб
    -0.06
     bus
    -0.06
    洞
    -0.06
    ності
    -0.06
    ，从
    -0.06
     жир
    -0.06
     b
    -0.06
     disadvantages
    -0.06
    POSITIVE LOGITS
     Gems
    0.07
    Parameters
    0.07
    （
    0.07
    ‫
    0.06
    (intent
    0.06
     McLaren
    0.06
    (init
    0.06
    HandlerContext
    0.06
    (option
    0.06
    (UInt
    0.06
    Act Density 0.000%

    No Known Activations