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

    Neuronpedia

    INDEX
    Explanations

    optimization/programming/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     С
    -0.08
     �
    -0.08
     Patterns
    -0.08
     Вс
    -0.08
     ସ
    -0.08
     включ
    -0.08
     нез
    -0.07
     Welcome
    -0.07
     готов
    -0.07
     holiday
    -0.07
    POSITIVE LOGITS
    gae
    0.09
    刷新
    0.09
     episod
    0.09
    育
    0.08
    iid
    0.08
    Worker
    0.08
    Replay
    0.08
     veilige
    0.08
     replay
    0.08
     업데이트
    0.08
    Act Density 0.003%

    No Known Activations