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

    Neuronpedia

    INDEX
    Explanations

    participate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sé
    -0.08
     ray
    -0.07
    鞘
    -0.07
    (copy
    -0.07
     уч
    -0.07
    占有
    -0.07
    垤
    -0.07
    沫
    -0.07
    滗
    -0.07
    镎
    -0.06
    POSITIVE LOGITS
     역시
    0.08
    んだろう
    0.07
     Robotics
    0.07
     겁니다
    0.07
     interface
    0.07
     Copenhagen
    0.07
     Obamacare
    0.07
    >();↵↵
    0.07
     serta
    0.07
     Architect
    0.07
    Act Density 0.004%

    No Known Activations