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

    Neuronpedia

    INDEX
    Explanations

    question mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    rap
    -0.06
    ，如果
    -0.06
     Roh
    -0.06
    .spark
    -0.06
    िनक
    -0.06
    rored
    -0.06
    后的
    -0.06
    Dire
    -0.06
    对
    -0.06
    POSITIVE LOGITS
     Anatomy
    0.08
     klient
    0.07
    uniform
    0.07
    -peer
    0.07
     будів
    0.06
    (Un
    0.06
     søker
    0.06
    ेण
    0.06
     dangling
    0.06
    .best
    0.06
    Act Density 0.004%

    No Known Activations