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

    Neuronpedia

    INDEX
    Explanations

    power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    募集
    -0.08
     mesmerizing
    -0.08
     irresistible
    -0.07
     inscr
    -0.07
    _nb
    -0.07
     breathtaking
    -0.07
    unifu
    -0.07
    紹介
    -0.07
     East
    -0.07
    _De
    -0.07
    POSITIVE LOGITS
    чиков
    0.08
    асын
    0.08
     борьбы
    0.08
     chết
    0.08
    чиком
    0.08
     :).
    0.08
     против
    0.08
     zusamm
    0.08
    чик
    0.08
    čen
    0.08
    Act Density 0.001%

    No Known Activations