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

    Neuronpedia

    INDEX
    Explanations

    Inventions and patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '))
    -0.08
    krę
    -0.07
     Review
    -0.07
    �
    -0.07
    isu
    -0.07
    /ion
    -0.07
    まと
    -0.07
    为什么不
    -0.07
     safely
    -0.07
    맣
    -0.07
    POSITIVE LOGITS
    表现出
    0.07
    ﳒ
    0.07
     Rabbit
    0.07
     Mei
    0.07
     iterating
    0.07
     martyr
    0.07
    堆积
    0.06
    broker
    0.06
    翟
    0.06
     söz
    0.06
    Act Density 0.024%

    No Known Activations