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

    Neuronpedia

    INDEX
    Explanations

    continuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    妇
    -0.06
     NC
    -0.06
    _LED
    -0.06
     Пло
    -0.06
    rious
    -0.06
     Ore
    -0.06
     Expires
    -0.06
    욱
    -0.06
    igers
    -0.06
    .sound
    -0.06
    POSITIVE LOGITS
     continuation
    0.32
    uation
    0.09
    uations
    0.08
     continu
    0.07
    adt
    0.07
    续
    0.07
    겼
    0.07
     remix
    0.07
     moh
    0.06
     ادامه
    0.06
    Act Density 0.002%

    No Known Activations